Search

Your search keyword '"Sangweni, Charles"' showing total 3 results
Start Over Author "Sangweni, Charles"
3 results on '"Sangweni, Charles"'

1. Prediction of Porous Media Fluid Flow with Spatial Heterogeneity Using Criss-Cross Physics-Informed Convolutional Neural Networks.

Author

Han, Jiangxia, Xue, Liang, Jia, Ying, Mwasamwasa, Mpoki Sam, Nanguka, Felix, Sangweni, Charles, Liu, Hailong, and Li, Qian

Abstract

Recent advances in deep neural networks have shed new light on physics, engineering, and scientific computing. Reconciling the data-centered viewpoint with physical simulation is one of the research hotspots. The physics-informed neural network (PINN) is currently the most general framework, which is more popular due to the convenience of constructing NNs and excellent generalization ability. The automatic differentiation (AD)-based PINN model is suitable for the homogeneous scientific problem; however, it is unclear how AD can enforce flux continuity across boundaries between cells of different properties where spatial heterogeneity is represented by grid cells with different physical properties. In this work, we propose a criss-cross physics-informed convolutional neural network (CC-PINN) learning architecture, aiming to learn the solution of parametric PDEs with spatial heterogeneity of physical properties. To achieve the seamless enforcement of flux continuity and integration of physical meaning into CNN, a predefined 2D convolutional layer is proposed to accurately express transmissibility between adjacent cells. The efficacy of the proposed method was evaluated through predictions of several petroleum reservoir problems with spatial heterogeneity and compared against state-of-the-art (PINN) through numerical analysis as a benchmark, which demonstrated the superiority of the proposed method over the PINN. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

2. Prediction of Porous Media Fluid Flow with Spatial Heterogeneity Using Criss-Cross Physics-Informed Convolutional Neural Networks.

Author

Jiangxia Han, Liang Xue, Ying Jia, Mwasamwasa, Mpoki Sam, Nanguka, Felix, Sangweni, Charles, Hailong Liu, and Qian Li

Abstract

Recent advances in deep neural networks have shed new light on physics, engineering, and scientific computing. Reconciling the data-centered viewpoint with physical simulation is one of the research hotspots. The physics-informed neural network (PINN) is currently the most general framework, which is more popular due to the convenience of constructing NNs and excellent generalization ability. The automatic differentiation (AD)-based PINN model is suitable for the homogeneous scientific problem; however, it is unclear how AD can enforce flux continuity across boundaries between cells of different properties where spatial heterogeneity is represented by grid cells with different physical properties. In this work, we propose a criss-cross physics-informed convolutional neural network (CC-PINN) learning architecture, aiming to learn the solution of parametric PDEs with spatial heterogeneity of physical properties. To achieve the seamless enforcement of flux continuity and integration of physical meaning into CNN, a predefined 2D convolutional layer is proposed to accurately express transmissibility between adjacent cells. The efficacy of the proposed method was evaluated through predictions of several petroleum reservoir problems with spatial heterogeneity and compared against state-of-the-art (PINN) through numerical analysis as a benchmark, which demonstrated the superiority of the proposed method over the PINN. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

3. ICDP workshop on the Lake Tanganyika Scientific Drilling Project: A late Miocene-present record of climate, rifting, and ecosystem evolution from the world's oldest tropical lake

Author

Russell, James, Barker, P A, Cohen, Andrew S, Ivory, Sarah J, Kimirei, I A, Lane, Christine S, Leng, Melanie J., Maganza, Neema, McGlue, Michael Matthew, Msaky, Emma S, Noren, Anders J, Boush, Lisa Park, Salzburger, Walter, Scholz, Christopher A, Tiedemann, Ralph, Nuru, Shaidu, Albrecht, Christian, Ali, Rahma, Arrowsmith, Ramón Ja, Asanga, Danstan, Asmerom, Yemane, Bakundukize, Charles, Bauersachs, Thorsten, Beck, Catherine C, Berke, Melissa A, Beverley, Emily, Blaauw, Martin, Brown, Erik T, Campisano, Christopher J, Carrapa, Bárbara, Castaûeda, Isla, Dee, Sylvia G, Deino, Alan L, Ebinger, Cynthia J, Ellis, Geoffrey S, Foerster, Verena E, Fontijn, Karen, Gehrels, George E, Indemaur, Adrian, Jovanovska, Elena, Junginger, Annett, Kaboth, Stefanie, Kallmeyer, Jens, King, John W, Konecky, Bronwen L, Mark, Darren F, McIntyre, Peter B, Michel, Ellinor, Mkuu, Doreen, Morgan, Leah, Mtetela, Cassy, Muderwha, Nshombo, Muirhead, James D, Mumbi, Cassian T, Muschick, Mo, Nahimana, David, Ngowi, Venosa, Njiko, Pashcal, Nkenyeli, Simon, Nkotagu, Hudson H, Ntakimazi, Gaspard, Oppo, Davide, Purkamo, Lotta, Rick, Jessica A, Roberts, Helen M, Ronco, Fabrizia, Sangweni, Charles, Shaghude, Yohanna W, Shigela, Josephat, Shillington, Donna J, Sophia, Chen Shuang, Sier, Mark Jan, Soreghan, Michael James, Spanbauer, Trisha L, Spencer-Jones, Charlotte L, Staff, Richard A, Stone, Jeffery R, Todd, Jonathan A, Trauth, Martin H, Van Bocxlaer, Bert, Viehberg, Finn A, Vogel, Hendrik, Vonhof, Hubert, Wolff, Christian, Wu, Qinglong, Yost, Chad L, Zeeden, Christian, Russell, James, Barker, P A, Cohen, Andrew S, Ivory, Sarah J, Kimirei, I A, Lane, Christine S, Leng, Melanie J., Maganza, Neema, McGlue, Michael Matthew, Msaky, Emma S, Noren, Anders J, Boush, Lisa Park, Salzburger, Walter, Scholz, Christopher A, Tiedemann, Ralph, Nuru, Shaidu, Albrecht, Christian, Ali, Rahma, Arrowsmith, Ramón Ja, Asanga, Danstan, Asmerom, Yemane, Bakundukize, Charles, Bauersachs, Thorsten, Beck, Catherine C, Berke, Melissa A, Beverley, Emily, Blaauw, Martin, Brown, Erik T, Campisano, Christopher J, Carrapa, Bárbara, Castaûeda, Isla, Dee, Sylvia G, Deino, Alan L, Ebinger, Cynthia J, Ellis, Geoffrey S, Foerster, Verena E, Fontijn, Karen, Gehrels, George E, Indemaur, Adrian, Jovanovska, Elena, Junginger, Annett, Kaboth, Stefanie, Kallmeyer, Jens, King, John W, Konecky, Bronwen L, Mark, Darren F, McIntyre, Peter B, Michel, Ellinor, Mkuu, Doreen, Morgan, Leah, Mtetela, Cassy, Muderwha, Nshombo, Muirhead, James D, Mumbi, Cassian T, Muschick, Mo, Nahimana, David, Ngowi, Venosa, Njiko, Pashcal, Nkenyeli, Simon, Nkotagu, Hudson H, Ntakimazi, Gaspard, Oppo, Davide, Purkamo, Lotta, Rick, Jessica A, Roberts, Helen M, Ronco, Fabrizia, Sangweni, Charles, Shaghude, Yohanna W, Shigela, Josephat, Shillington, Donna J, Sophia, Chen Shuang, Sier, Mark Jan, Soreghan, Michael James, Spanbauer, Trisha L, Spencer-Jones, Charlotte L, Staff, Richard A, Stone, Jeffery R, Todd, Jonathan A, Trauth, Martin H, Van Bocxlaer, Bert, Viehberg, Finn A, Vogel, Hendrik, Vonhof, Hubert, Wolff, Christian, Wu, Qinglong, Yost, Chad L, and Zeeden, Christian

Abstract

The Neogene and Quaternary are characterized by enormous changes in global climate and environments, including global cooling and the establishment of northern high-latitude glaciers. These changes reshaped global ecosystems, including the emergence of tropical dry forests and savannahs that are found in Africa today, which in turn may have influenced the evolution of humans and their ancestors. However, despite decades of research we lack long, continuous, well-resolved records of tropical climate, ecosystem changes, and surface processes necessary to understand their interactions and influences on evolutionary processes. Lake Tanganyika, Africa, contains the most continuous, long continental climate record from the mid-Miocene (∼ 10 Ma) to the present anywhere in the tropics and has long been recognized as a top-priority site for scientific drilling. The lake is surrounded by the Miombo woodlands, part of the largest dry tropical biome on Earth. Lake Tanganyika also harbors incredibly diverse endemic biota and an entirely unexplored deep microbial biosphere, and it provides textbook examples of rift segmentation, fault behavior, and associated surface processes. To evaluate the interdisciplinary scientific opportunities that an ICDP drilling program at Lake Tanganyika could offer, more than 70 scientists representing 12 countries and a variety of scientific disciplines met in Dar es Salaam, Tanzania, in June 2019. The team developed key research objectives in basin evolution, source-to-sink sedimentology, organismal evolution, geomicrobiology, paleoclimatology, paleolimnology, terrestrial paleoecology, paleoanthropology, and geochronology to be addressed through scientific drilling on Lake Tanganyika. They also identified drilling targets and strategies, logistical challenges, and education and capacity building programs to be carried out through the project. Participants concluded that a drilling program at Lake Tanganyika would produce the first continuous Mioce, SCOPUS: ar.j, info:eu-repo/semantics/published

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results