{"id":243254,"date":"2025-05-06T13:39:28","date_gmt":"2025-05-06T11:39:28","guid":{"rendered":"https:\/\/cimne.com\/research\/research-clusters\/machine-learning-and-models-in-hydro-environmental-engineering\/machine-learning-in-civil-engineering\/"},"modified":"2026-04-17T14:33:22","modified_gmt":"2026-04-17T12:33:22","slug":"aprenentatge-automatic-enginyeria-civil","status":"publish","type":"page","link":"https:\/\/cimne.com\/ca\/recerca\/clusters-de-recerca\/aprenentatge-automatic-models-enginyeria-hidroambiental\/aprenentatge-automatic-enginyeria-civil\/","title":{"rendered":"Aprenentatge autom\u00e0tic en enginyeria civil"},"content":{"rendered":"

[et_pb_section fb_built=”1″ disabled_on=”off|off|off” admin_label=”Intro desktop” module_id=”first-section” _builder_version=”4.27.3″ positioning=”none” custom_margin=”0px||0px||false|false” custom_padding=”0px||0px||false|false” border_width_all=”1px” border_color_all=”#d9d9d9″ border_width_top=”1px” border_color_top=”#d9d9d9″ border_width_right=”1px” border_color_right=”#d9d9d9″ border_width_left=”1px” border_color_left=”#d9d9d9″ collapsed=”off” global_colors_info=”{}”][et_pb_row column_structure=”2_3,1_3″ _builder_version=”4.27.6″ _module_preset=”e065a7aa-3e21-43af-9b0f-36301287f1d9″ global_colors_info=”{}” hover_enabled=”0″ sticky_enabled=”0″][et_pb_column type=”2_3″ _builder_version=”4.27.6″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ custom_padding=”0px|3%||3%|false|true” custom_padding_tablet=”0px|3%||3%|false|true” custom_padding_phone=”0px|3%||3%|false|true” custom_padding_last_edited=”on|phone” hover_enabled=”0″ border_width_right_tablet=”0px” border_width_right_phone=”0px” border_width_right_last_edited=”on|phone” global_colors_info=”{}” sticky_enabled=”0″][et_pb_divider color=”#004996″ divider_position=”center” _builder_version=”4.27.0″ _module_preset=”default” width=”85px” module_alignment=”left” custom_margin=”||0px||false|false” global_colors_info=”{}”][\/et_pb_divider][et_pb_text admin_label=”Subtitle” _builder_version=”4.27.5″ _module_preset=”0cd9f80c-570e-4179-9fd1-d5366dd9bb29″ global_colors_info=”{}”]Aprenentatge autom\u00e0tic i models en enginyeria hidroambiental[\/et_pb_text][et_pb_heading title=”@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF90aXRsZSIsInNldHRpbmdzIjp7ImJlZm9yZSI6IiIsImFmdGVyIjoiIn19@” admin_label=”H1″ _builder_version=”4.27.5″ _dynamic_attributes=”title” _module_preset=”4c5ef66f-50cd-42c5-b88c-a74fdcea313a” global_colors_info=”{}”][\/et_pb_heading][et_pb_text admin_label=”Title” _builder_version=”4.27.5″ _module_preset=”6d55416f-9dec-40a9-9718-5879084be1a8″ global_colors_info=”{}”]Investigador principal[\/et_pb_text][et_pb_text admin_label=”Contact point” _builder_version=”4.27.5″ _module_preset=”f199e95e-376a-4f66-b51b-482255312542″ global_colors_info=”{}”]Fernando Salazar[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.27.6″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ custom_padding=”0px|3%||3%|false|true” custom_padding_tablet=”0px|6%||6%|false|true” custom_padding_phone=”||||false|true” hover_enabled=”0″ border_width_right_tablet=”0px” border_width_right_phone=”0px” border_width_right_last_edited=”on|phone” global_colors_info=”{}” border_width_left=”1px” border_color_left=”#d9d9d9″ sticky_enabled=”0″][et_pb_code admin_label=”Back button” _builder_version=”4.27.4″ _dynamic_attributes=”link_option_url” _module_preset=”default” text_orientation=”right” module_alignment=”right” custom_margin=”||25px||false|false” link_option_url=”@ET-DC@eyJkeW5hbWljIjp0cnVlLCJjb250ZW50IjoicG9zdF9saW5rX3VybF9wYWdlIiwic2V0dGluZ3MiOnsicG9zdF9pZCI6Ijc5In19@” locked=”off” global_colors_info=”{}”]Enrere<\/span>[\/et_pb_code][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/05\/ML-header.jpg” title_text=”Cap\u00e7alera ML” force_fullwidth=”on” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”default” height=”220px” custom_margin=”||50px||false|false” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ admin_label=”Cluster Data Menu Desktop” _builder_version=”4.27.4″ _module_preset=”3fa56594-59c4-4608-b810-3a571a22796b” collapsed=”off” global_colors_info=”{}”][et_pb_row column_structure=”1_4,1_4,1_4,1_4″ _builder_version=”4.27.0″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ locked=”off” global_colors_info=”{}”][et_pb_column type=”1_4″ _builder_version=”4.27.0″ _module_preset=”default” custom_padding=”20px|0px||0px|false|true” custom_padding_tablet=”50px|0%|||false|false” custom_padding_phone=”50px||||false|false” custom_padding_last_edited=”off|desktop” border_width_right_tablet=”0px” border_width_right_phone=”0px” border_width_right_last_edited=”on|phone” global_colors_info=”{}”][et_pb_heading title=”Visi\u00f3 general” admin_label=”Overview” module_id=”overview-item” module_class=” tab-item” _builder_version=”4.27.6″ _module_preset=”default” title_level=”h2″ title_font=”Lora|600|on||||||” title_text_align=”center” title_text_color=”#444444″ title_font_size=”1.1rem” title_line_height=”1.5rem” width=”100%” custom_margin=”0px||0px||false|false” custom_padding=”0px||0px||false|false” hover_enabled=”0″ custom_css_main_element=”padding-bottom: 16px;” global_colors_info=”{}” background__hover_enabled=”off|desktop” title_text_color__hover_enabled=”on|hover” title_text_color__hover=”#004996″ sticky_enabled=”0″][\/et_pb_heading][\/et_pb_column][et_pb_column type=”1_4″ _builder_version=”4.27.0″ _module_preset=”default” custom_padding=”20px|3%||0px|false|false” custom_padding_tablet=”50px|0%|||false|false” custom_padding_phone=”50px||||false|false” custom_padding_last_edited=”off|desktop” border_width_right_tablet=”0px” border_width_right_phone=”0px” border_width_right_last_edited=”on|phone” global_colors_info=”{}”][et_pb_heading title=”Recerca” admin_label=”Research” module_id=”research-item” module_class=” tab-item” _builder_version=”4.27.6″ _module_preset=”default” title_level=”h2″ title_font=”Lora|600|on||||||” title_text_align=”center” title_text_color=”#444444″ title_font_size=”1.1rem” title_line_height=”1.5rem” width=”100%” custom_margin=”0px||0px||false|false” custom_padding=”0px||0px||false|false” hover_enabled=”0″ custom_css_main_element=”padding-bottom: 16px;” global_colors_info=”{}” background__hover_enabled=”off|desktop” title_text_color__hover_enabled=”on|hover” title_text_color__hover=”#004996″ sticky_enabled=”0″][\/et_pb_heading][\/et_pb_column][et_pb_column type=”1_4″ _builder_version=”4.27.0″ _module_preset=”default” custom_padding=”20px|0px||0px|false|true” custom_padding_tablet=”50px|0%|||false|false” custom_padding_phone=”50px||||false|false” custom_padding_last_edited=”off|desktop” border_width_right_tablet=”0px” border_width_right_phone=”0px” border_width_right_last_edited=”on|phone” global_colors_info=”{}”][et_pb_heading title=”Membres” admin_label=”Staff” module_id=”staff-item” module_class=”tab-item” _builder_version=”4.27.6″ _module_preset=”default” title_level=”h2″ title_font=”Lora|600|on||||||” title_text_align=”center” title_text_color=”#444444″ title_font_size=”1.1rem” title_line_height=”1.5rem” width=”100%” custom_margin=”0px||0px||false|false” custom_padding=”0px||0px||false|false” hover_enabled=”0″ custom_css_main_element=”padding-bottom: 16px;” global_colors_info=”{}” title_text_color__hover_enabled=”on|hover” title_text_color__hover=”#004996″ sticky_enabled=”0″][\/et_pb_heading][\/et_pb_column][et_pb_column type=”1_4″ _builder_version=”4.27.0″ _module_preset=”default” custom_padding=”20px|0px||0px|false|true” custom_padding_tablet=”50px|0%|||false|false” custom_padding_phone=”50px||||false|false” custom_padding_last_edited=”off|desktop” border_width_right_tablet=”0px” border_width_right_phone=”0px” border_width_right_last_edited=”on|phone” global_colors_info=”{}”][et_pb_heading title=”Projectes” admin_label=”Projects” module_id=”projects-item” module_class=”tab-item” _builder_version=”4.27.6″ _module_preset=”default” title_level=”h2″ title_font=”Lora|600|on||||||” title_text_align=”center” title_text_color=”#444444″ title_font_size=”1.1rem” title_line_height=”1.5rem” width=”100%” custom_margin=”0px||0px||false|false” custom_padding=”0px||0px||false|false” hover_enabled=”0″ custom_css_main_element=” padding-bottom: 16px;” global_colors_info=”{}” title_text_color__hover_enabled=”on|hover” title_text_color__hover=”#004996″ sticky_enabled=”0″][\/et_pb_heading][et_pb_heading title=”Publicacions” disabled_on=”on|on|on” admin_label=”Publications” module_id=”publications-item” module_class=”tab-item” _builder_version=”4.27.6″ _module_preset=”default” title_level=”h2″ title_font=”Lora|600|on||||||” title_text_align=”center” title_text_color=”#444444″ title_font_size=”1.1rem” title_line_height=”1.5rem” width=”100%” custom_margin=”0px||0px||false|false” custom_padding=”0px||0px||false|false” hover_enabled=”0″ custom_css_main_element=” padding-bottom: 16px;” disabled=”on” global_colors_info=”{}” title_text_color__hover_enabled=”on|hover” title_text_color__hover=”#004996″ sticky_enabled=”0″][\/et_pb_heading][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ admin_label=”Overview Tab” module_class=”overview-content tab-content” _builder_version=”4.27.4″ _module_preset=”fed47f3e-3ebe-4259-a156-523c8e0b8966″ collapsed=”off” global_colors_info=”{}”][et_pb_row _builder_version=”4.27.4″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ custom_margin=”|0px||0px|false|false” custom_padding=”50px|0px|50px|0px|true|false” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_text _builder_version=”4.27.0″ _module_preset=”default” text_text_color=”#004996″ text_font_size=”1.5rem” text_line_height=”1.8rem” width=”50%” width_tablet=”100%” width_phone=”100%” width_last_edited=”on|desktop” custom_margin=”||||true|false” global_colors_info=”{}”]<\/p>\n

Aquest grup desenvolupa eines basades en ML per resoldre problemes complexos d’enginyeria en els camps hidr\u00e0ulic, geomec\u00e0nic i ambiental, combinant dades de sensors, modelatge num\u00e8ric i solucions pr\u00e0ctiques de programari per a l’an\u00e0lisi predictiva i el suport a la decisi\u00f3.<\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row admin_label=”1px Line Row” _builder_version=”4.27.4″ _module_preset=”default” width=”100%” max_width=”2500px” custom_margin=”0px||0px||true|false” custom_padding=”0px||0px||true|false” collapsed=”on” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”][et_pb_divider show_divider=”off” _builder_version=”4.27.4″ _module_preset=”default” width=”100%” height=”0px” custom_margin=”0px||0px||true|false” custom_padding=”0px||0px||true|false” border_width_bottom=”1px” border_color_bottom=”#d9d9d9″ global_colors_info=”{}”][\/et_pb_divider][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_3,1_3,1_3″ _builder_version=”4.27.4″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ custom_margin=”|0px||0px|false|false” custom_padding=”50px|0px|50px|0px|false|false” global_colors_info=”{}”][et_pb_column type=”1_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_text _builder_version=”4.27.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

El Grup de Recerca en Aprenentatge Autom\u00e0tic en Enginyeria Civil del CIMNE se centra en la resoluci\u00f3 de problemes complexos d’enginyeria mitjan\u00e7ant la integraci\u00f3 de t\u00e8cniques d’aprenentatge autom\u00e0tic (ML) amb dades de sensors, simulacions num\u00e8riques i modelatge f\u00edsic.<\/p>\n

<\/p>\n

El grup t\u00e9 una \u00e0mplia experi\u00e8ncia en l’aplicaci\u00f3 de m\u00e8todes ML a infraestructures hidr\u00e0uliques, incloses preses, sobreeixidors i sistemes de subministrament d’aigua, amb una s\u00f2lida traject\u00f2ria en el monitoratge de la salut estructural, la detecci\u00f3 d’anomalies i el manteniment predictiu.<\/p>\n

<\/p>\n

M\u00e9s enll\u00e0 de la hidr\u00e0ulica, el grup tamb\u00e9 explora aplicacions en geomec\u00e0nica, monitoritzaci\u00f3 ambiental i processos industrials. Les activitats de recerca abasten tota la respiraci\u00f3 de ML, des del preprocessament de dades i el desenvolupament d’algorismes fins a la quantificaci\u00f3 i interpretabilitat de la incertesa. <\/p>\n

<\/p>\n

 <\/p>\n

[\/et_pb_text][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_text _builder_version=”4.27.0″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

Les t\u00e8cniques inclouen models de conjunt, aprenentatge profund i estrat\u00e8gies h\u00edbrides que combinen ML amb models num\u00e8rics com CFD i DEM. El grup mant\u00e9 una forta orientaci\u00f3 pr\u00e0ctica, desenvolupant solucions de programari personalitzades amb interf\u00edcies d’usuari per al desplegament en el m\u00f3n real i expandint-se a \u00e0rees com la predicci\u00f3 de la qualitat de l’aigua i la desinfecci\u00f3 d’aig\u00fces residuals. <\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=”1_3,1_3,1_3″ _builder_version=”4.27.4″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ custom_margin=”|0px||0px|false|false” custom_padding=”|0px|50px|0px|false|false” locked=”off” global_colors_info=”{}”][et_pb_column type=”1_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/05\/ML_1.jpg” title_text=”ML_1″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”100%” module_alignment=”center” height=”220px” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/05\/ML_2.jpg” title_text=”ML_2″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”100%” module_alignment=”center” height=”220px” global_colors_info=”{}”][\/et_pb_image][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ admin_label=”Research Tab” module_id=”section-splitter-menu” module_class=”research-content tab-content” _builder_version=”4.27.4″ _module_preset=”fed47f3e-3ebe-4259-a156-523c8e0b8966″ locked=”off” collapsed=”off” global_colors_info=”{}”][et_pb_row column_structure=”1_4,3_4″ gutter_width=”2″ admin_label=”\u00c0rees de recerca” _builder_version=”4.27.4″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ custom_padding=”0px|0px|32px|0px|false|false” locked=”off” collapsed=”off” global_colors_info=”{}”][et_pb_column type=”1_4″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_heading title=”\u00c0rees de recerca” admin_label=”H2″ _builder_version=”4.27.4″ _module_preset=”default” title_level=”h2″ title_text_color=”#004996″ title_font_size=”2rem” title_line_height=”2rem” global_colors_info=”{}”][\/et_pb_heading][\/et_pb_column][et_pb_column type=”3_4″ _builder_version=”4.27.4″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ border_color_right=”#d9d9d9″ global_colors_info=”{}”][et_pb_heading title=”Activitats de recerca amb t\u00e8cniques d'aprenentatge autom\u00e0tic” admin_label=”Machine learning for dam behavior prediction” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”2rem” title_line_height=”2.25rem” global_colors_info=”{}”][\/et_pb_heading][et_pb_heading title=”Aprenentatge autom\u00e0tic per a la predicci\u00f3 del comportament de la presa” admin_label=”Machine learning for dam behavior prediction” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h4″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” custom_padding=”0px|||||” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” global_colors_info=”{}”]<\/p>\n

Desenvolupament de metodologies i programari per a l’an\u00e0lisi de dades de monitoratge de preses, incloent la generaci\u00f3 de models predictius de ML i la seva interpretaci\u00f3, amb l’objectiu final de donar suport a la presa de decisions en seguretat de preses. Relacionat amb: Projecte DOLMEN<\/a> . <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra1.jpg” title_text=”Machlearn-1Ra1″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” global_colors_info=”{}”]<\/p>\n

Software per a l’avaluaci\u00f3 de la seguretat de les preses mitjan\u00e7ant ML: captures de pantalla de l’aplicaci\u00f3 SOLDIER<\/a>. GitHub repo.<\/a><\/span><\/p>\n

[\/et_pb_text][et_pb_gallery gallery_ids=”238190,238193″ posts_number=”2″ orientation=”portrait” show_title_and_caption=”off” show_pagination=”off” zoom_icon_color=”RGBA(255,255,255,0)” hover_overlay_color=”RGBA(255,255,255,0)” _builder_version=”4.27.4″ _module_preset=”default” module_alignment=”center” global_colors_info=”{}”][\/et_pb_gallery][et_pb_heading title=”Aprenentatge autom\u00e0tic avan\u00e7at per a la detecci\u00f3 i localitzaci\u00f3 d'anomalies” admin_label=”Advanced machine learning for anomaly detection and localization” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” global_colors_info=”{}”]<\/p>\n

Explorem les possibilitats de l’aprenentatge profund i altres algorismes avan\u00e7ats de ML com els autocodificadors per curar dades de monitoratge, detectar anomalies i localitzar possibles danys estructurals.<\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra2.png” title_text=”Machlearn-1Ra2″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Estructura de l’autocodificador (esquerra) i detecci\u00f3 de dades de monitoritzaci\u00f3 an\u00f2males (dreta). Font: https:\/\/doi.org\/10.1007\/s13349-025-00910-4. <\/p>\n

[\/et_pb_text][et_pb_heading title=”Noves eines computacionals per a l'avaluaci\u00f3 de la seguretat de preses basada en la fiabilitat ” admin_label=”New computational tools for reliability-based dam safety assessment ” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

\u00das de models ML per donar suport a l’an\u00e0lisi FEM per predir la resposta de la presa, inclosa la incertesa i l’an\u00e0lisi de riscos. Relacionat amb: Projecte TRISTAN<\/a> <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra3.png” title_text=”machlearn-1ra3″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Detecci\u00f3 d’anomalies en preses: exemple de xarxa de monitoratge (esquerra) i model num\u00e8ric per simular esdeveniments an\u00f2mals (dreta). Font: https:\/\/doi.org\/10.3390\/w13172387<\/a> <\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”An\u00e0lisi d'estructures hidr\u00e0uliques” admin_label=”New computational tools for reliability-based dam safety assessment ” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

An\u00e0lisi del rendiment hidr\u00e0ulic de sobreeixidors i sortides de fons combinant m\u00e8todes num\u00e8rics (PFEM, Free-Surface) i t\u00e8cniques ML.<\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra4.png” title_text=”machlearn-1ra4″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Rendiment hidr\u00e0ulic del sobreeixidor: exemple de geometria (esquerra) i relaci\u00f3 entre els valors observats i previstos dels models ML de capacitat de desc\u00e0rrega. Font: https:\/\/doi.org\/10.3390\/w11030544<\/a> <\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Optimitzaci\u00f3 intel\u00b7ligent de processos industrials ” admin_label=”Smart optimization of industrial processes ” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Suport i optimitzaci\u00f3 dels processos de disseny de deformaci\u00f3 met\u00e0l\u00b7lica rotacional. \u00das del marc Digital Twin basat en FEM combinat amb t\u00e8cniques de classificaci\u00f3 ML. Relacionat amb: Projecte OPTIPRO<\/a> <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra5.png” title_text=”machlearn-1ra5″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

An\u00e0lisi de processos de conformaci\u00f3 de metalls: equips industrials (esquerra) i GUI per a la parametritzaci\u00f3 de processos (dreta)<\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Qualitat de l'aigua i t\u00e8cniques de tractament de l'aigua” admin_label=”Water quality and water treatment techniques” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Aplicaci\u00f3 de models ML per a la predicci\u00f3 de l’estat de qualitat de l’aigua en masses d’aigua i avaluaci\u00f3 de tractaments avan\u00e7ats d’eliminaci\u00f3 de contaminants de l’aigua. Relacionat amb: DIGIT4WATER<\/a> Projecte <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra6.png” title_text=”Machlearn-1Ra6″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Predicci\u00f3 de tractaments avan\u00e7ats d’aig\u00fces residuals amb t\u00e8cniques ML. M\u00e9s informaci\u00f3: https:\/\/doi.org\/10.1016\/j.jenvman.2024.123537<\/a> <\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Previsi\u00f3 de la qualitat de l'aire” admin_label=”Air quality forecasting” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Aplicaci\u00f3 de models ML per a la predicci\u00f3 de l’estat de la qualitat de l’aire. Relacionat amb: PIKSEL<\/a>, Projectes PRONURB<\/a> . <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra7.png” title_text=”machlearn-1ra7″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Predicci\u00f3 basada en ML de la concentraci\u00f3 d’O3 troposf\u00e8ric a la plataforma PICSEL<\/a>.<\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Identificaci\u00f3 de perills per fallada de preses amb substituts ML” admin_label=”Identification of hazards due to dam failure with ML surrogates” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Estimaci\u00f3 autom\u00e0tica de possibles danys en cas de fallada d’embassaments fora corrent. Relacionat amb: Projecte ACR\u00d2POLIS<\/a> . <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra8.png” title_text=”machlearn-1ra8″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Captures de pantalla del programari ACR\u00d2POLIS<\/a>. Disponible a GitHub<\/a>. <\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Calibratge de models num\u00e8rics amb ML ” admin_label=”Air quality forecasting” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Calibratge de par\u00e0metres del M\u00e8tode d’Elements Discrets (DEM) combinant c\u00e0lcul num\u00e8ric d’alt rendiment amb ML. Relacionat amb: TRISTAN,<\/a> Projectes HIRMA<\/a> . <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-1ra9.png” title_text=”machlearn-1ra9″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||32px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Calibratge dels par\u00e0metres DEM del comportament de l’argila: model num\u00e8ric per simular proves de comportament de l’argila (esquerra), i an\u00e0lisi de calibratge mitjan\u00e7ant ML (centre i dreta). Font: https:\/\/doi.org\/10.1007\/s40571-022-00550-1<\/a> <\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Activitats de recerca amb m\u00e8todes num\u00e8rics” admin_label=”Machine learning for dam behavior prediction” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”2rem” title_line_height=”2.25rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_heading title=”Comportament termomec\u00e0nic de preses de formig\u00f3” admin_label=”Thermo-mechanical behavior of concrete dams” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Simulaci\u00f3 del comportament de la presa de formig\u00f3 durant les etapes de construcci\u00f3 i operaci\u00f3 integrant c\u00e0rregues termomec\u00e0niques d’alt detall. Relacionat amb: Projecte ACOMBO<\/a> ; Aplicaci\u00f3 de programari ‘DamApplication<\/a>‘ (integrada en el marc Kratos). <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-2ra1.jpg” title_text=”Machlearn-2RA1″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Modelitzaci\u00f3 de preses de formig\u00f3: simulaci\u00f3 d’etapes de construcci\u00f3 (esquerra), camp de despla\u00e7aments (centre) i camp de tensions (dreta). Font: https:\/\/doi.org\/10.1007\/s11831-020-09439-9<\/a> <\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Disseny de sobreeixidors de blocs en forma de falca ” admin_label=”Design of wedge-shaped block spillways ” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Simulaci\u00f3 CFD mitjan\u00e7ant modelatge FEM euleriano i simulaci\u00f3 d’estabilitat de blocs mitjan\u00e7ant modelatge DEM. Relacionat amb: Projecte PABLO<\/a> . <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-2ra2.jpg” title_text=”machlearn-2ra2″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Simulaci\u00f3 de sobreeixidors de blocs en forma de falca: an\u00e0lisi hidr\u00e0ulica (esquerra), disseny de blocs (centre) i an\u00e0lisi d’estabilitat de blocs (dreta)<\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Disseny industrial de portes de fusibles de preses ” admin_label=”Industrial design of dam fuse gates ” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Simulacions d’interacci\u00f3 fluid-s\u00f2lid mitjan\u00e7ant modelitzaci\u00f3 PFEM+DEM per calcular els seg\u00fcents processos: cabal de desc\u00e0rrega per a diferents posicions de porta, velocitat de caiguda de portes i for\u00e7a d’impacte porta-paret. Relacionat amb: Projecte COFRE<\/a> . <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-2ra3.jpg” title_text=”machlearn-2ra3″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Simulaci\u00f3 de portes de fusibles: disseny de geometria (esquerra), simulaci\u00f3 2D d’interacci\u00f3 fluid-s\u00f2lid (centre) i simulaci\u00f3 3D (dreta)<\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”An\u00e0lisi CFD d'estructures hidr\u00e0uliques: sobreeixidors altament convergents, modelitzaci\u00f3 de conques d'aquietaci\u00f3 i sistemes de drenatge ” admin_label=”Air quality forecasting” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Simulaci\u00f3 de fen\u00f2mens hidr\u00e0ulics 3D complexos, mitjan\u00e7ant models FEM i PFEM, com ara la posici\u00f3 en superf\u00edcie lliure de salt hidr\u00e0ulic, camps de pressi\u00f3 i velocitat i identificaci\u00f3 de zones amb risc d’erosi\u00f3. <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-2ra4.jpg” title_text=”machlearn-2ra4″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

An\u00e0lisi CFD d’estructures hidr\u00e0uliques: sobreeixidors altament convergents (esquerra) i simulaci\u00f3 de conca de quietud (dreta)<\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”An\u00e0lisi del comportament del llast ferroviari amb el m\u00e8tode dels elements discrets (DEM)” admin_label=”Air quality forecasting” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Simulaci\u00f3 d’infraestructures ferrovi\u00e0ries contra accions de canvi clim\u00e0tic i avaluaci\u00f3 de la resposta de llast ferroviari mitjan\u00e7ant model DEM. Relacionat amb: Projecte RESILTRACK<\/a> . <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-2ra5.jpg” title_text=”machlearn-2ra5″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Simulaci\u00f3 d’infraestructures ferrovi\u00e0ries: simulaci\u00f3 del comportament del llast (esquerra), an\u00e0lisi de calibratge (centre) i simulaci\u00f3 d’infraestructures ferrovi\u00e0ries (dreta)<\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Modelitzaci\u00f3 num\u00e8rica de xarxes de distribuci\u00f3 d'aigua (WDN)” admin_label=”Numerical modelling of Water Distribution Networks (WDN)” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Desenvolupament de models num\u00e8rics per a la simulaci\u00f3 de fuites mitjan\u00e7ant solucionadors avan\u00e7ats impulsats per pressi\u00f3. Relacionat amb: Projecte SMILER<\/a> . <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-2ra6.jpg” title_text=”Machlearn-2Ra6″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Esquema metodol\u00f2gic d’utilitat num\u00e8rica avan\u00e7ada per simular casos massius d’escenaris de fuites en WDN<\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Enfocaments h\u00edbrids” admin_label=”Machine learning for dam behavior prediction” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”2rem” title_line_height=”2.25rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_heading title=”Predicci\u00f3 flexible i precisa del comportament de la presa” admin_label=”Flexible and accurate prediction of dam behavior” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Enfocaments intel\u00b7ligents per augmentar la flexibilitat i la precisi\u00f3 de la predicci\u00f3 del comportament de les preses combinant resultats de m\u00e8todes num\u00e8rics i models ML utilitzant dades de monitoratge. Relacionat amb: projecte DOLMEN.<\/a> <\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-3ra1.jpg” title_text=”Machlearn-3Ra1″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Predicci\u00f3 del despla\u00e7ament de la presa d’arc amb enfocaments h\u00edbrids.<\/span><\/p>\n

[\/et_pb_text][et_pb_heading title=”Predicci\u00f3 de cabals a curt termini amb models h\u00edbrids” admin_label=”Air quality forecasting” _builder_version=”4.27.4″ _module_preset=”default” title_level=”h3″ title_font=”|700|||||||” title_font_size=”1.5rem” title_line_height=”1.8rem” locked=”off” global_colors_info=”{}”][\/et_pb_heading][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Metodologies per combinar resultats de models num\u00e8rics 2D (basats en el programari IBER) amb models basats en ML que consideren els valors de pluja i cabal passat per obtenir prediccions precises i r\u00e0pides de 3 hores d’antelaci\u00f3 del cabal en esdeveniments d’inundaci\u00f3.<\/span><\/p>\n

[\/et_pb_text][et_pb_image src=”https:\/\/cimne.com\/wp-content\/uploads\/2025\/08\/machlearn-3ra2.jpg” title_text=”Machlearn-3Ra2″ show_in_lightbox=”on” align=”center” module_class=”fit-img” _builder_version=”4.27.4″ _module_preset=”1f4e2daa-a4c7-40db-b678-0b21ac6841bd” width=”60%” width_tablet=”60%” width_phone=”100%” width_last_edited=”on|phone” module_alignment=”center” locked=”off” global_colors_info=”{}”][\/et_pb_image][et_pb_text _builder_version=”4.27.4″ _module_preset=”default” text_font_size=”12px” text_orientation=”center” width=”60%” module_alignment=”center” custom_padding=”||20px||false|false” locked=”off” global_colors_info=”{}”]<\/p>\n

Hidrograma observat versus prediccions amb enfocaments h\u00edbrids. Font: https:\/\/doi.org\/10.1080\/02626667.2024.2426720<\/a> <\/span><\/p>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row admin_label=”1px Line Row” _builder_version=”4.27.4″ _module_preset=”default” width=”100%” max_width=”2500px” custom_margin=”0px||0px||true|false” custom_padding=”0px||0px||true|false” collapsed=”on” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”][et_pb_divider show_divider=”off” _builder_version=”4.27.4″ _module_preset=”default” width=”100%” height=”0px” custom_margin=”0px||0px||true|false” custom_padding=”0px||0px||true|false” border_width_bottom=”1px” border_color_bottom=”#d9d9d9″ global_colors_info=”{}”][\/et_pb_divider][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ admin_label=”Staff Tab” module_class=”staff-content tab-content” _builder_version=”4.27.4″ _module_preset=”fed47f3e-3ebe-4259-a156-523c8e0b8966″ collapsed=”off” global_colors_info=”{}”][et_pb_row _builder_version=”4.27.0″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ collapsed=”off” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_code disabled_on=”off|off|off” admin_label=”WS code” _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

<\/div>\n

[\/et_pb_code][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ admin_label=”Projects Tab” module_class=”projects-content tab-content” _builder_version=”4.27.4″ _module_preset=”fed47f3e-3ebe-4259-a156-523c8e0b8966″ collapsed=”off” global_colors_info=”{}”][et_pb_row column_structure=”1_4,3_4″ disabled_on=”off|off|off” admin_label=”Tabs Nav” _builder_version=”4.27.2″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ global_colors_info=”{}”][et_pb_column type=”1_4″ module_id=”project-items” _builder_version=”4.27.2″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_blurb title=”Projectes en curs” use_icon=”on” font_icon=”||fa||900″ icon_color=”rgba(2,160,165,0.5)” image_icon_width=”24px” icon_alignment=”left” content_max_width=”100%” admin_label=”Ongoing projects” module_id=”ongoing-projects-item” module_class=”projects-nav-item nav-item-active” _builder_version=”4.27.4″ _module_preset=”2be94eae-2349-4743-a4da-6a4100bff33f” header_level=”h6″ header_text_align=”left” header_text_color=”rgba(2,160,165,0.5)” header_font_size=”1.5rem” header_line_height=”1.8rem” image_icon_custom_margin=”|||30px|false|false” width=”100%” module_alignment=”left” custom_margin=”0px||0px||false|false” custom_padding=”10px||0px||false|false” header_text_align_last_edited=”off|desktop” custom_css_blurb_image=”margin-bottom: 0px;” custom_css_blurb_title=”padding-left: 10px;” border_width_left=”1px” border_color_left=”rgba(2,160,165,0.5)” locked=”off” global_colors_info=”{}”][\/et_pb_blurb][et_pb_blurb title=”Projectes finalitzats” use_icon=”on” font_icon=”||fa||400″ icon_color=”rgba(2,160,165,0.5)” image_icon_width=”24px” icon_alignment=”left” content_max_width=”100%” admin_label=”Finished projects” module_id=”finished-projects-item” module_class=”projects-nav-item ” _builder_version=”4.27.4″ _module_preset=”2be94eae-2349-4743-a4da-6a4100bff33f” header_level=”h6″ header_text_align=”left” header_text_color=”rgba(2,160,165,0.5)” header_font_size=”1.5rem” header_line_height=”1.8rem” image_icon_custom_margin=”||0px|30px|false|false” width=”100%” module_alignment=”left” custom_margin=”0px||0px||false|false” custom_padding=”10px||0px||false|false” header_text_align_last_edited=”off|desktop” custom_css_blurb_image=”margin-bottom: 0px;” custom_css_blurb_title=”padding-left: 10px;” border_width_left=”1px” border_color_left=”rgba(2,160,165,0.5)” global_colors_info=”{}” custom_css_blurb_image_last_edited=”off|desktop”][\/et_pb_blurb][\/et_pb_column][et_pb_column type=”3_4″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_code disabled_on=”off|off|off” admin_label=”WS code” _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

<\/div>\n

[\/et_pb_code][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ disabled_on=”on|on|on” admin_label=”Publications Tab” module_class=”publications-content tab-content” _builder_version=”4.27.4″ _module_preset=”fed47f3e-3ebe-4259-a156-523c8e0b8966″ disabled=”on” collapsed=”off” global_colors_info=”{}”][et_pb_row column_structure=”1_4,3_4″ _builder_version=”4.27.0″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ global_colors_info=”{}”][et_pb_column type=”1_4″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_heading title=”Cerca” _builder_version=”4.27.2″ _module_preset=”default” title_level=”h6″ title_text_color=”#02a0a5″ title_font_size=”1.5rem” title_line_height=”1.9rem” global_colors_info=”{}”][\/et_pb_heading][et_pb_code disabled_on=”off|off|off” admin_label=”WS publications filter” module_class=”rtd-layout” _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”]<\/p>\n

<\/form>\n

[\/et_pb_code][\/et_pb_column][et_pb_column type=”3_4″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_code admin_label=”WS publications-container” _builder_version=”4.27.4″ _module_preset=”default” locked=”off” global_colors_info=”{}”]<\/p>\n

<\/div>\n

[\/et_pb_code][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ disabled_on=”off|off|off” admin_label=”Related News” module_class=”section-news” _builder_version=”4.27.4″ background_color=”rgba(2,160,165,0.15)” positioning=”none” custom_margin=”0px||0px||false|false” custom_padding=”0px||0px||false|false” border_width_all=”1px” border_color_all=”#d9d9d9″ border_width_top=”1px” border_color_top=”#d9d9d9″ border_width_right=”1px” border_color_right=”#d9d9d9″ border_width_left=”1px” border_color_left=”#d9d9d9″ locked=”off” collapsed=”off” global_colors_info=”{}”][et_pb_row column_structure=”1_3,2_3″ _builder_version=”4.27.0″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ global_colors_info=”{}”][et_pb_column type=”1_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_heading title=”Not\u00edcies relacionades” _builder_version=”4.27.0″ _module_preset=”default” title_level=”h2″ title_text_color=”#004996″ title_font_size=”3rem” title_line_height=”3rem” title_font_size_tablet=”2rem” title_font_size_phone=”2rem” title_font_size_last_edited=”on|phone” title_line_height_tablet=”2.1rem” title_line_height_phone=”2.1rem” title_line_height_last_edited=”on|phone” global_colors_info=”{}”][\/et_pb_heading][\/et_pb_column][et_pb_column type=”2_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ global_colors_info=”{}”][et_pb_blog posts_number=”2″ include_categories=”263″ admin_label=”Secondary news” _builder_version=”4.27.4″ _module_preset=”3ed04698-5e33-431b-875a-29f1e90b0248″ global_colors_info=”{}”][\/et_pb_blog][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ disabled_on=”off|off|off” admin_label=”Related News Bottom” module_id=”section-news-bottom” _builder_version=”4.27.0″ background_color=”rgba(2,160,165,0.15)” positioning=”none” custom_margin=”0px||0px||false|false” custom_padding=”0px||0px||false|false” border_width_all=”1px” border_color_all=”#d9d9d9″ border_width_top=”1px” border_color_top=”#d9d9d9″ border_width_right=”1px” border_color_right=”#d9d9d9″ border_width_left=”1px” border_color_left=”#d9d9d9″ collapsed=”off” global_colors_info=”{}”][et_pb_row column_structure=”2_3,1_3″ disabled_on=”off|off|off” _builder_version=”4.27.0″ _module_preset=”c7c24b71-68f1-4ba2-bc79-49dcbcce5ea1″ global_colors_info=”{}”][et_pb_column type=”2_3″ disabled_on=”on|on|off” _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ custom_padding=”0px|3%||3%|false|false” border_width_right=”1px” border_color_right=”#d9d9d9″ global_colors_info=”{}”][et_pb_text disabled_on=”on|on|off” admin_label=”Empty element” _builder_version=”4.27.0″ _module_preset=”default” text_font=”|600||on|||||” text_text_color=”#444444″ text_font_size=”1.1rem” text_line_height=”1.5rem” positioning=”relative” position_origin_a=”bottom_left” position_origin_r=”bottom_left” width=”100%” height=”80px” custom_padding=”||4%||false|false” link_option_url=”#” text_text_color_tablet=”#000000″ text_text_color_phone=”#000000″ text_text_color_last_edited=”on|tablet” text_orientation_tablet=”left” text_orientation_phone=”left” text_orientation_last_edited=”off|desktop” module_alignment_tablet=”right” module_alignment_phone=”right” module_alignment_last_edited=”on|phone” global_colors_info=”{}”][\/et_pb_text][\/et_pb_column][et_pb_column type=”1_3″ _builder_version=”4.27.0″ _module_preset=”56e57fde-4561-4cf6-a771-0a733a7201b1″ custom_padding=”0px|3%||3%|false|false” global_colors_info=”{}”][et_pb_text admin_label=”View More” _builder_version=”4.27.4″ _module_preset=”e6f2ca4a-5bde-4214-9440-f02003a84dc0″ global_colors_info=”{}”]<\/p>\n

<\/span>
<\/span>
M\u00e9s not\u00edcies<\/a><\/span><\/div>\n

[\/et_pb_text][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ admin_label=”WS attr” _builder_version=”4.27.4″ _module_preset=”default” custom_margin=”0px|0px|0px|0px|true|true” custom_padding=”0px|0px|0px|0px|true|true” global_colors_info=”{}”][et_pb_row admin_label=”WS attr” _builder_version=”4.27.4″ _module_preset=”b5c6bc94-6a1a-411b-8024-a0dbaf36c71f” custom_margin=”0px|0px|0px|0px|true|true” custom_padding=”0px|0px|0px|0px|true|true” global_colors_info=”{}”][et_pb_column type=”4_4″ _builder_version=”4.27.4″ _module_preset=”default” global_colors_info=”{}”][et_pb_code admin_label=”WS attr” _builder_version=”4.27.4″ _module_preset=”default” custom_margin=”0px|0px|0px|0px|true|true” custom_padding=”0px|0px|0px|0px|true|true” global_colors_info=”{}”]<\/p>\n

<\/div>\n

[\/et_pb_code][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"

Aprenentatge autom\u00e0tic i models en enginyeria hidroambientalInvestigador principalFernando SalazarAquest grup desenvolupa eines basades en ML per resoldre problemes complexos d’enginyeria en els camps hidr\u00e0ulic, geomec\u00e0nic i ambiental, combinant dades de sensors, modelatge num\u00e8ric i solucions pr\u00e0ctiques de programari per a l’an\u00e0lisi predictiva i el suport a la decisi\u00f3.El Grup de Recerca en Aprenentatge Autom\u00e0tic en […]<\/p>\n","protected":false},"author":2,"featured_media":0,"parent":226575,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","slim_seo":{"title":"Aprenentatge autom\u00e0tic en enginyeria civil - CIMNE","description":"Aprenentatge autom\u00e0tic i models en enginyeria hidroambientalInvestigador principalFernando Salazar Enrere Aquest grup desenvolupa eines basades en ML per resold"},"footnotes":""},"class_list":["post-243254","page","type-page","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/cimne.com\/ca\/wp-json\/wp\/v2\/pages\/243254","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cimne.com\/ca\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/cimne.com\/ca\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/cimne.com\/ca\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/cimne.com\/ca\/wp-json\/wp\/v2\/comments?post=243254"}],"version-history":[{"count":0,"href":"https:\/\/cimne.com\/ca\/wp-json\/wp\/v2\/pages\/243254\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/cimne.com\/ca\/wp-json\/wp\/v2\/pages\/226575"}],"wp:attachment":[{"href":"https:\/\/cimne.com\/ca\/wp-json\/wp\/v2\/media?parent=243254"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}