Reliable estimation of region-wide rice yield is vital for food security and agricultural management. Field-scale models have increased our understanding of rice yield and its estimation under theoretical environmental conditions. However, they offer little information on spatial variability effects on farm-scale yield. Remote Sensing (RS) is a useful tool to upscale yield estimates from farm scales to regional levels. Much research used RS with rice models for reliable yield estimation. As several countries start to operationalize rice monitoring systems, it is needed to synthesize current literature to identify knowledge gaps, to improve estimation accuracies, and to optimize processing. This paper critically reviewed significant developments in using geospatial methods, imagery, and quantitative models to estimate rice yield. First, essential characteristics of rice were discussed as detected by optical and radar sensors, band selection, sensor configuration, spatial resolution, mapping methods, and biophysical variables of rice derivable from RS data. Second, various empirical, process-based, and semi-empirical models that used RS data for spatial estimation of yield were critically assessed – discussing how major types of models, RS platforms, data assimilation algorithms, canopy state variables, and RS variables can be integrated for yield estimation. Lastly, to overcome current constraints and to improve accuracies, several possibilities were suggested – adding new modeling modules, using alternative canopy variables, and adopting novel modeling approaches. As rice yields are expected to decrease due to global warming, geospatial rice yield estimation techniques are indispensable tools for climate change assessments. Future studies should focus on resolving the current limitations of estimation by precise delineation of rice cultivars, by incorporating dynamic harvesting indices based on climatic drivers, using innovative modeling approaches with machine learning.

Paddy rice agriculture is practiced in both rain-fed and irrigated ecosystems in the Philippines. However, small farms are prevalent in the region, and current satellite-based mapping techniques do not distinguish between the two ecosystems at farm scales. This study developed an approach to rapidly map irrigated and rain-fed paddy rice in Iloilo, Philippines at 10 m resolutions using Google Earth Engine. This approach used an ensemble of classifiers based on time-series vegetation indices to produce dry and wet seasonal maps for the entire province. Results showed a predominance of rain-fed rice areas in both seasons, with irrigated rice making up only one-fourth of the total rice area. The overall accuracy was achieved at 68% for the dry season and 75% for the wet season based on ground-acquired points and very high-resolution imagery. The two types of paddies were classified at accuracies up to 87%. Furthermore, the land cover maps showed a strong agreement with the municipal statistics. The resultant maps complement current official statistics and demonstrate the prowess of phenology-based mapping to create paddy inventories in a timely manner to inform food security and agricultural policies.

Accurate approaches to aboveground biomass (AGB) estimation are required to support appraisal of the effectiveness of land use measures, which seek to protect grazing-adapted grasslands atop the Qinghai-Tibet Plateau (QTP). This methodological study assesses the effectiveness of one commonly used visible band vegetation index, Red Green Blue Vegetation Index (RGBVI), obtained from unmanned aerial vehicle (UAV), in estimating AGB timely and accurately at the local scale, seeking to improve the estimation accuracy by taking into account in situ collected information on disturbed grassland. Particular emphasis is placed upon the mapping and quantification of areas disturbed by grazing (simulated via mowing) and plateau pika (Ochotona curzoniae) that have led to the emergence of bare ground. The initial model involving only RGBVI performed poorly in AGB estimation by underestimating high AGB by around 10% and overestimating low AGB by about 10%. The estimation model was modified by the mowing intensity ratio and bare ground metrics. The former almost doubled the estimation accuracy from R² = 0.44 to 0.81. However, this modification caused the bare ground AGB to be overestimated by about 38 and 19 g m⁻² for 2018 and 2019, respectively. Although further modification of the model by bare ground metrics improved the accuracy slightly to 0.88, it markedly reduced the overestimation of low AGB values. It is recommended that grazing intensity be incorporated into the micro-scale estimation of AGB, together with the bare ground modification metrics, especially for severely disturbed meadows with a sizable portion of bare ground.

This study utilized the Analytic Hierarchical Process and spatial analysis using various datasets to produce sub-provincial vulnerability maps with 20 km resolution. Five (5) indicators for exposure, four (4) for sensitivity and seven (7) for adaptive capacity were selected and weighted using aggregated rankings from twenty-three (23) experts. Based on these indicators, gridded maps of exposure, sensitivity, adaptive capacity, and vulnerability were produced. Using river basins as the unit of analysis, the Pampanga River Basin was determined to be the most vulnerable, followed by the Agus River Basin, having the highest sensitivity, and Buayan River Basin, having the lowest adaptive capacity. These areas have large agricultural regions and river systems with high flooding risk. Coastal regions in southern Mindanao and eastern Visayas were also highly vulnerable to flooding. High poverty rates with high dependence on agricultural incomes and low adaptive capacities characterize these areas. Vulnerability hotspots can easily be identified through these maps, which have value in planning initiative to reduce potential damages of floods to agricultural areas.

Seasonal fires in northern Thailand are a persistent environmental and public health concern, yet existing fire probability mapping approaches in Thailand rely heavily on subjective multi-criteria analysis (MCA) methods and temporally static data aggregation methods. To address these limitations, we present a flexible, replicable, and operationally viable seasonal fire probability mapping methodology using a Random Forest (RF) machine learning model in the Google Earth Engine (GEE) platform. We trained the model on historical fire occurrence and fire predictor layers from 2016–2023 and applied it to 2024 conditions to generate a probabilistic fire prediction. Our novel approach improves upon existing operational methods and scientific literature in several ways. It uses a more representative sample design which is agnostic to the burn history of fire presences and absences, pairs fire and fire predictor data from each year to account for interannual variation in conditions, empirically refines the most influential fire predictors from a comprehensive set of predictors, and provides a reproducible and accessible framework using GEE. Predictor variables include both socioeconomic and environmental drivers of fire, such as topography, fuels, potential fire behavior, forest type, vegetation characteristics, climate, water availability, crop type, recent burn history, and human influence and accessibility. The model achieves an Area Under the Curve (AUC) of 0.841 when applied to 2016–2023 data and 0.848 when applied to 2024 data, indicating strong discriminatory power despite the additional spatial and temporal variability introduced by our sample design. The highest fire probabilities emerge in forested and agricultural areas at mid elevations and near human settlements and roads, which aligns well with the known anthropogenic drivers of fire in Thailand. Distinct areas of model uncertainty are also apparent in cropland and forests which are only burned intermittently, highlighting the importance of accounting for localized burning cycles. Variable importance analysis using the Gini Impurity Index identifies both natural and anthropogenic predictors as key and nearly equally important predictors of fire, including certain forest and crop types, vegetation characteristics, topography, climate, human influence and accessibility, water availability, and recent burn history. Our findings demonstrate the heavy influence of data preprocessing and model design choices on model results. The model outputs are provided as interpretable probability maps and the methods can be adapted to future years or augmented with local datasets. Our methodology presents a scalable advancement in wildfire probability mapping with machine learning and open-source tools, particularly for data-constrained landscapes. It will support Thailand’s fire managers in proactive fire response and planning and also inform broader regional fire risk assessment efforts.