Remote Sensing and Machine Learning in Water Stress Detection, With an Emphasis on Applications in Maize Farming

DR ANNA MSIGWA

Agriculture represents almost 30% of Tanzania’s GDP, with three-quarters of the country’s workforce involved. Yet productivity is low, with modest progress over the past two decades. The productivity of major crops such as maize and wheat will decline. Post-harvest losses, below-average rainfall, pests and high input prices are expected in 2022/2023. With a projected population growth of some 69.7 million people by 2050, the anticipated doubling of food demand cannot yet be met.

At grassroots level, farmers have bought into research, implementing terraces for water and soil conservation. Dr Anna Msigwa studies the efficient use of water for agriculture in the Pangani Basin in Tanzania by incorporating seasonal land-use dynamics into water analysis models. Her unique approach has already been used to study agricultural water uses across Africa and by PhD students at Vrije Universiteit Brussel in Belgium.

To successfully reduce water usage, the early detection and monitoring of plant responses to stress in crops are mandatory. Remote sensing will produce the necessary data for precision agriculture. This, in turn, promises to close the yield gap by optimising food production using the proper management practices (at the right place and time) while keeping the consumption of resources at an environmentally sustainable level. This balance will benefit ecosystems and human well-being, and enhancing the agricultural sector’s outputs while enhancing nutrition and improving health.

Dr Msigwa will develop a machine learning-based crop water stress mapping system. The system will make use of thermal infrared multi-/hyperspectral remote sensing images to collect ground data. The Kikuletwa catchment area (about 6 077km2) is within nine districts in the Arusha, Manyara and Kilimanjaro regions. To monitor the water stress status of maize in-field, stem water potential (SWP) measurements will be captured using a customised pressure chamber. The SWP values will indicate whether crops are water-stressed – and targeted for irrigation.

The project works closely with OIKOS, a Tanzanian NGO that promotes the protection of biodiversity and the sustainable use of natural resources as tools in the fight against climate change. The NGO will help communicate with farmers involved in the project. The research will lead to an application for water stress detection with results mapping an overview of management practices, soil types and characteristics, and up-to-date spatial and temporal climate variability in the catchment.

Dr Anna Msigwa is a lecturer in the Department of Water Environmental Sciences and Engineering at the Nelson Mandela African Institution of Science and Technology (NM-AIST), Tanzania. She holds a PhD in Engineering Sciences from Vrije Universiteit Brussel, Belgium, a master’s degree in Hydrology and Water Resources Engineering from NM-AIST and a bachelor’s degree in Environmental Engineering from Ardhi University, Tanzania. Dr Msigwa is a hydrologist and water management expert who researches water resource management in Africa and climate-smart agricultural water management strategies using remote sensing technologies.

Dr Anna Msigwa

FAR-LEAF Research Fellow
Nelson Mandela African Institution of Science and Technology
Tanzania

The Future Africa Research Leader Fellowship (FAR-LeaF) is a fellowship programme, focussed on developing transdisciplinary research and leadership skills, to address the complex, inter-linked challenges of health, well-being, and environmental risks in Africa.