In making irrigation decisions, farmers typically rely on local observation and experience, such as observing crops and neighbors’ actions. Research has mainly focused on understanding crop water requirements to improve farming practices, but it is important to acknowledge that farmers have unique perspectives, access to diverse local “signals”, and experience. The challenge is to strike a balance between complex technical assessments of field conditions (the science) and harnessing farmers’ skills to manage their irrigation in ways that maximize yield and quality. This study established a basis for specifying minimum data requirements for pragmatic, but not necessarily perfect, irrigation decision-making for small-scale Vietnamese coffee farmers. This study focuses on three areas in Dak Lak province in the Central Highlands of Vietnam. To explore the role of monitoring in irrigation management, two contrasting monitoring systems were set up to collect soil, weather, and irrigation data. We also compared a variety of water balance models with different data requirements, with a focus on processes that used “passive data collection”, i.e., farmers do not manually collect data, rather data can be accessed readily from external sources. In Vietnam, traditional hosepipe irrigation is applied where it is impractical to know the volume of applied water. The proposed Low Data Model (LDM) is suited to more informed irrigation scheduling decisions, which have potential to improve the likelihood of coffee growers adopting measurement-based decision-making. While researchers may seek a detailed daily sub-millimeter understanding of soil water dynamics, farmers require practical decision support if there is to be any adoption of improved methods. This study offers a simple and practical approach for irrigation scheduling rather than a model using numerically perfect data that is unachievable in the field. The work demonstrates that on-site rainfall data is essential. However, other data can be collected passively to reduce the burden of data collection on users. This approach may enhance the likelihood of model-based irrigation scheduling being adopted by coffee farmers in Vietnam.

The extraction and utilization of fossil fuels from mining areas worldwide have led to significant CO ₂ emissions. Post-mining landscapes also present challenging environmental conditions that can hinder effective land use. In recent years, the installation of photovoltaic (PV) and floating photovoltaic (FPV) systems in abandoned mining areas has emerged as a promising solution. However, large-scale solar energy potential assessment methods in these areas are still lacking. To address these challenges, SolarMiner is presented, combining the approaches of both computer vision model and satellite imagery. By segmenting and identifying different types of mining areas and calculating their respective surface areas, the installation potential of both traditional PV and FPV systems is calculated. The model performance is validated using data from a province of China, Shanxi. Results reveal that there is a substantial solar energy potential in the mining areas, exceeding 1446 TWh annually, which was 6.52 times the total electricity consumption of Shanxi in 2023. The levelized costs of electricity range from 0.023 to 0.042 USD/kWh.