![Marcial Sandoval-Gastelum profile picture Marcial Sandoval-Gastelum profile picture](/sites/default/files/styles/thumbnail/public/module-files/mis_staff_sync/profile-images/73461_2024_9_1_1_7.jpg?itok=266dnDbx)
Marcial Sandoval-Gastelum
Researcher
Exploratory Modeling of Human-natural Systems Research Group
Advancing Systems Analysis Program
Contact
Biography
Marcial Sandoval-Gastelum is a researcher in the Exploratory Modeling of Human-Natural Systems Research Group of the IIASA Advancing Systems Analysis Program. His primary research interest lies in advancing artificial intelligence, with a focus on developing and applying state-of-the-art deep learning architectures for addressing climate change.He has over six years of experience in the artificial intelligence field and holds a master's degree in Computer Science from the Universidad Autonoma de Baja California in Mexico. Additionally, he has specialized in deep learning and natural language processing through certifications from DeepLearning.ai.
Sandoval-Gastelum has accumulated extensive expertise in various deep learning architectures applied across multiple domains. During his master's degree studies, his research journey included contributions to human action recognition using inertial data and classical artificial intelligence techniques. In 2019, he worked as a guest researcher at IIASA, contributing to the development of a crop type image recognition system using convolutional neural networks. After completing his master's degree, he collaborated with University College London (UCL) on research related to human action recognition using graph convolutional neural networks.
Currently, he is involved in developing SmartLinker, a multi-agent, multi-objective reinforcement learning algorithm for land use modeling within the FABLE consortium. His current research focuses on applying state-of-the-art deep learning architectures such as Deep Q-Learning, Transformers, and large language models to address climate change.
Last update: 15 JUL 2024
Publications
FABLE (2024). Transforming food and land systems to achieve the SDGs. In: The SDGs and the UN Summit of the Future. Sustainable Development Report 2024. Eds. Sachs, J.D., Lafortune, G., & Fuller, G., pp. 50-82 Dublin, Ireland: Dublin University Press. ISBN 978-0-903200-18-9 10.25546/108572.
Orduña-Cabrera, F. , Sandoval-Gastelum, M., McCallum, I. , See, L. , Fritz, S. , Karanam, S., Sturn, T., Javalera Rincón, V. , & Gonzalez-Navarro, F.F. (2023). Investigating the Use of Street-Level Imagery and Deep Learning to Produce In-Situ Crop Type Information. Geographies 3 (3) 563-573. 10.3390/geographies3030029.
Alsawadi, M.S., Sandoval-Gastelum, M., Danish, I., & Rio, M. (2023). BlazePose-Based Action Recognition with Feature Selection Using Stochastic Fractal Search Guided Whale Optimization. In: 2023 International Conference on Control, Automation and Diagnosis (ICCAD). pp. 1-5 Rome, Italy: IEEE. 10.1109/ICCAD57653.2023.10152320.