Mohammad Kakooei

Mohammad Kakooei's research focuses on the intersection of Machine Learning (ML), Artificial Intelligence (AI), and Earth Observation (EO), with applications in disaster management, land cover mapping, urban studies, socio-economic analysis, and sustainable development. He combines advanced AI methods, satellite imagery, cloud computing, and big-data analytics to address real-world environmental and societal challenges.

His work includes post-disaster damage assessment, wildfire monitoring, urban expansion analysis, land cover and wetland mapping, and large-scale socio-economic studies such as poverty and wealth mapping across Africa. These projects have been conducted through collaborations with institutions including KTH Royal Institute of Technology, Chalmers University of Technology, Harvard University, and Linköping University.

In addition, he has experience in high-performance computing using GPU programming with CUDA, as well as the development of AI-enabled medical devices integrating computer vision, embedded systems, and sensor technologies.

His research outputs include publications in leading journals, publicly available datasets and web applications, patents, and contributions to international scientific collaborations and peer review activities.

Mohammad Kakooei has taught and contributed to courses in machine learning, artificial intelligence, computer vision, remote sensing, and digital systems at graduate and undergraduate levels. Selected courses include:

• Introduction to Data Science and AI – Chalmers University of Technology
• Design of AI Systems – Chalmers University of Technology
• Deep Statistics: AI and Earth Observations for Sustainable Development – Harvard University
• AI for Earth and Environmental Sciences – University of Gothenburg
• Microprocessor and Assembly Language – Babol Noshirvani University of Technology
• Digital Systems – Babol Noshirvani University of Technology

Mohammad Kakooei has collaborated with researchers, universities, and organizations across world on interdisciplinary projects related to AI, Earth Observation, sustainability, and socio-economic development. His collaborations include research partnerships with KTH Royal Institute of Technology, Harvard University, University of Gothenburg, AI Sweden, and UNHCR. 

• Kakooei, Mohammad, James Bailie, Markus B. Pettersson, Albin Söderberg, Albin Becevic, and Adel Daoud. "A high resolution urban and rural settlement map of Africa using deep learning and satellite imagery." Scientific Reports 16, no. 1 (2026): 637.
• Kakooei, Mohammad, and Adel Daoud. "Increasing the confidence of predictive uncertainty: earth observations and deep learning for poverty estimation." IEEE Transactions on Geoscience and Remote Sensing (2024). 
• Kakooei, Mohammad, and Yasser Baleghi. "Mapping Building Heights at Large Scales Using Sentinel-1 Radar Imagery and Nighttime Light Data." Remote Sensing 16, no. 18 (2024): 3371. 
• Pettersson, Markus B., Mohammad Kakooei, Julia Ortheden, Fredrik D. Johansson, and Adel Daoud. "Time series of satellite imagery improve deep learning estimates of neighborhood-level poverty in africa." In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pp. 6165-6173. 2023. 
• Kakooei, Mohammad, and Yasser Baleghi. "Fusion of vertical and oblique images using Intra-Cluster-Classification for building damage assessment." Computers and Electrical Engineering 105 (2023): 108536. 
• Kakooei, Mohammad, and Yasser Baleghi. "Spatial-Temporal analysis of urban environmental variables using building height features." Urban Climate 52 (2023): 101736. 
• Amani, Meisam, Sahel Mahdavi, Mohammad Kakooei, Arsalan Ghorbanian, Brian Brisco, Evan R. DeLancey, Souleymane Toure, and Eugenio Landeiro Reyes. "Wetland change analysis in Alberta, Canada using four decades of landsat imagery." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14 (2021): 10314-10335. 
• Kakooei, Mohammad, Yasser Baleghi, and Meisam Amani. "Adaptive thresholding for detecting building facades with or without openings in single-view oblique remote sensing images." Journal of Applied Remote Sensing 15, no. 3 (2021): 036511-036511. 
• Amani, Meisam, Arsalan Ghorbanian, Seyed Ali Ahmadi, Mohammad Kakooei, Armin Moghimi, S. Mohammad Mirmazloumi, Sayyed Hamed Alizadeh Moghaddam et al. "Google earth engine cloud computing platform for remote sensing big data applications: A comprehensive review." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 13 (2020): 5326-5350.
• Ghorbanian, Arsalan, Mohammad Kakooei, Meisam Amani, Sahel Mahdavi, Ali Mohammadzadeh, and Mahdi Hasanlou. "Improved land cover map of Iran using Sentinel imagery within Google Earth Engine and a novel automatic workflow for land cover classification using migrated training samples." ISPRS Journal of Photogrammetry and Remote Sensing 167 (2020): 276-288.
• Kakooei, Mohammad, and Amir Tabatabaei. "A fast parallel GPS acquisition algorithm based on hybrid GPU and multi-core CPU." Wireless Personal Communications 104 (2019). 

Public Datasets and Products 
To support the research community and broader societal needs, I have released several publicly
available datasets and products. These include: 

• Iran Land Cover Map Link 
• Time-Series Africa Urban-Rural Map Link
• Time-Series Africa Poverty Map Link 
• ELC10: European 10 m resolution land cover map 2018 Link

Web Applications 
To enhance accessibility and usability, I have developed web applications associated with these
datasets and products. These applications include: 

• Urban Area Extraction Link 
• Africa Poverty Map Link 
• Africa Urban-Rural Map Link