António, Valinho

Bio

Mr. Valinho is a Visiting Scholar at the Xylem Lab in the Department of Geographical Sciences at the University of Maryland. He is also a Lecturer at Universidade Rovuma, Mozambique, and a Ph.D. candidate at the African Centre of Excellence in Internet of Things (ACEIoT), University of Rwanda.

His research is motivated by the need for up-to-date and reliable crop production statistics across sub-Saharan Africa. While machine learning (ML) and Earth observation have proven effective for crop monitoring in large-scale and data-rich agricultural systems of developed economies, their operational application within African agricultural statistics agencies remains limited. Valinho's work focuses on developing GeoAI approaches that integrate geospatial data, ML, and crop modeling to improve crop type classification and yield estimation in smallholder farming systems, supporting the production of timely agricultural information.

At the Xylem Lab, Valinho is developing a physics-guided GeoAI framework that combines the WOFOST crop growth model, Ensemble Kalman Filter-based assimilation of leaf area index and soil moisture observations, and ML techniques to enhance crop yield estimation. His research is conducted through collaborations spanning the University of Maryland, Carnegie Mellon University Africa, and the University of Rwanda, contributing to advances in precision agriculture and GeoAI.

Degrees

  • M.Sc. in Applied Computing, Federal University of Pampa, Brazil

  • B.Sc. in Computer Science, Lurio University, Mozambique

Areas of Interest

  • Machine Learning
  • Physics-Guided Machine Learning
  • Geospatial Data Science
  • Precision Agriculture
  • Food Security

Research Topics

  • Geospatial Information Science and Remote Sensing
  • Remote Sensing
  • Valinho António, Geoffrey Kimani, Eric Umohoza, and Moise Busogi (2024). Cross-Regional Transferability of AI Crop-Type Mapping: Insights and Challenges. In Proceedings of the 2024 International Conference on Information Technology for Social Good (GoodIT '24). Association for Computing Machinery, New York, NY, USA, 453–461. https://doi.org/10.1145/3677525.3678696.

  • António, V., Umuhoza, E., Bakunzibake, P., Busogi, M. (2026). Application of Machine Learning on Satellite Imagery for Crop-Type Classification in sub-Saharan Africa. In: Choudrie, J., Tuba, E., Perumal, T., Joshi, A. (eds) ICT for Intelligent Systems. ICTIS 2025. Smart Innovation, Systems and Technologies, vol 126. Springer, Singapore. https://doi.org/10.1007/978-981-95-1361-1_35.

  • António, Valinho and Umuhoza, Eric and Nakalembe, Catherine and Bakunzibake, Pierre and Busogi, Moise, GLSTM-MLP: a deep learning framework for crop type classification in smallholder farms with PlanetScope images (2025). Available at SSRN: http://dx.doi.org/10.2139/ssrn.5896643

  • António, Valinho and Nakalembe, Catherine and Busogi, Moise and Umuhoza, Eric, GeoAI-Based Crop Yield Estimation in Africa: A Systematic and Bibliometric Literature Review With Comparisons to Major Agricultural Producers (2026). Available at SSRN: http://dx.doi.org/10.2139/ssrn.6538738

1