Geology topics

Donghoon Lee

Publications and source records attributed to Donghoon Lee.

4 recordsLinked to original sources

USGS2025

HarvestStat Africa – Harmonized subnational crop statistics for sub-Saharan Africa

Sub-Saharan Africa (SSA) faces severe agricultural data scarcity amidst high food insecurity and a large agricultural yield gap, making crop production data crucial for understanding and enhancing food systems. To address this gap, HarvestStat Africa presents the largest compilation of open-access subnational crop statistics and time-series across SSA. Based on agricultural statistics collated by USAID’s Famine Early Warning Systems Network, the subnational crop statistics are standardized and calibrated across changing administrative units to produce consistent and continuous time-series. The dataset includes 546,605 records, primarily spanning from 1980 to 2022, detailing crop production, harvested areas, and yields for 33 countries and 90 crop types, including key cereals in SSA such as wheat, maize, rice, sorghum, barley, millet, and fonio. This new dataset enhances our understanding of how climate variability and change influence agricultural production, supports subnational food system analysis, and aids in operational yield forecasting. As an open-source resource, it sets an important precedent for sharing subnational crop statistics to inform decision-making and modeling efforts.

Scientific Data - Nature↗

USGS2024

Testing spatial out-of-sample area of influence for grain forecasting models

We examine the factors that determine if a grain forecasting model fit to one region can be transferred to another region. Prior research has proposed examining the area of applicability (AoA) of a model based on structurally similar characteristics in the Earth Observation predictors and weights based on the model derived feature importance. We expand on and evaluate this approach in the context of grain yield forecasting in Sub-Saharan Africa. Specifically, we evaluate an AoA methodology established for generating raster surfaces and apply it to vector supported grain data. We fit a series of ensemble tree models both within single countries and across multiple sets of countries and then test those models in countries excluded from the training set. We then calculate and decompose AoA measures and examine several different performance metrics. We find that the spatial transfer accuracy does not vary across season but does vary by average rainfall and across high, medium, and low yielding regions. In general, areas with higher yields and medium to high average rainfall tend to have higher accuracy for both model training and transfer. Finally, we find that fitting models with multiple countries provides more accurate out-of-sample estimates when compared to models fitted to a single country.

Enivronmental Research Letters↗

USGS2024

ENSO-based outlook of droughts and agricultural outcomes in Afghanistan

Drought is one of the key drivers of food insecurity in Afghanistan, which is among the most food insecure countries in the world. In this study, we build on previous research and seek to answer the central question: “What is the influence of El Niño-Southern Oscillation (ENSO) on drought outlooks and agricultural yield outcome in Afghanistan, and how do these influences vary spatially ?” We do so by utilizing multiple indicators of droughts and available wheat yield reports. We find a clear distinction in the probability of drought (defined as being in the lower tercile) in Afghanistan during La Niña compared to El Niño events since 1981. The probability of drought in Afghanistan increased during La Niña, particularly in the North, Northeast, and West regions. La Niña events are related to an increase in the probability of snow drought, particularly in parts of the Amu Darya basin. It is found that relative to El Niño events, snow water equivalent [total runoff] during La Niña events January–March (March–July total runoff) decreases between 9% and 30% (28%–42%) for the five major basins in the country. The probability of agricultural drought during La Niña events is found to be higher than 70% in the rainfed and irrigated areas of the Northeast, North, and West regions. This result is at least partly supported by reported wheat yield composites related to La Niña events that tend to be lower than for El Niño events across all regions in the case of rainfed wheat (statistically significant in Northeast, West, and South regions) and in some cases for irrigated wheat. The results of this study have direct implications for improving early warning of worsening food insecurity in Afghanistan during La Niña events, given that we now have long-lead and skillful forecasts of ENSO up to 18–24 months in advance, which could potentially be used to provide earlier warning of worsening food insecurity in Afghanistan

Weather and Climate Extremes↗

USGS2022

Maize yield forecasts for Sub-Saharan Africa using Earth Observation data and machine learning

Food insecurity continues to grow in Sub-Saharan Africa (SSA). In 2019, chronically malnourished people numbered nearly 240 million, or 20% of the population in SSA. Globally, numerous efforts have been made to anticipate potential droughts, crop conditions, and food shortages in order to improve early warning and risk management for food insecurity. To support this goal, we develop an Earth Observation (EO) and machine-learning-based operational, subnational maize yield forecast system and evaluate its out-of-sample forecast skills during the growing seasons for Kenya, Somalia, Malawi, and Burkina Faso. In general, forecast skills improve substantially during the vegetative growth period (VP) and gradually during the reproductive development period (RP). Thus, mid-season assessment can provide effective early warning months before harvest. Skillful forecasts (Nash Sutcliffe Efficiency (NSE) > 0.6 and Mean Absolute Percentage Error (MAPE) < 20%) appear approximately two dekads after the VP; for example, skillful forecasts appear in May in Kenya and Somalia, January in Malawi, and July in Burkina Faso. During model development, effective EO features are also identified, such as precipitation and available water during VP, and dry days and extreme temperatures in early VP. Compared to monthly standard EO features, sub-monthly (dekadal), non-standard, and serial EO features significantly improve forecast skills by ＋ 0.3 NSE and -10% of MAPE, demonstrating the ability to precisely and effectively capture favorable or detrimental crop development conditions. Finally, skillful forecasts and practical utility are demonstrated in the recent normal and dry years in each region. Overall, the developed yield forecasting system can provide skillful predictions during the growing season, supporting regional and international agricultural decision-making processes, including informing food-security planning and management, thereby helping to mitigate food shortages caused by unfavorable climate conditions.

Global Food Security↗