Stuart G. Edris
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Stuart G. Edris has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
Jordan I. Christian
Department of Atmospheric Sciences, University of North Dakota, Grand Forks, North Dakota
4 shared publicationsJeffrey B. Basara
Department of Environmental, Earth, and Atmospheric Sciences, University of Massachusetts Lowell, Lowell, Massachusetts
3 shared publicationsAmy McGovern
School of Meteorology, University of Oklahoma, Norman, Oklahoma
2 shared publicationsBradley G. Illston
2 shared publicationsEric D. Hunt
2 shared publicationsHenry Olayiwola
School of Meteorology, University of Oklahoma, Norman, Oklahoma
2 shared publications
Latest Publications
- 1 July 2025
- Published by American Meteorological Society in Artificial Intelligence for the Earth Systems
- Vol. 4 (3)
Evaluation of Flash Drought Identification with Machine Learning Techniques. Part I: Traditional Machine Learning Algorithms
Drought is an extreme event that can have a number of impacts on water resources and agricultural productivity. To mitigate the impacts, many studies have focused on improving drought predictions. As part of this, machine learning (ML) has emerged as a useful tool for drought identification and prediction, which has been shown to skillfully predict seasonal-scale droughts. In addition, a subset of drought, termed flash drought, has gained increased attention due to its rapid development and difficulty to predict. Studies focused on flash droughts have found a number of variables that accurately characterize their rapidly evolving conditions. However, while much work has been conducted to investigate flash droughts, limited work has been completed using ML techniques. This study investigated the ability of ML algorithms to represent and predict flash drought events via two parts. The first part focused on standard ML techniques such as random forests, Ada boosting, and support vector machines, while the second part focused on neural-network-based models. The ML models were trained on a set of key flash drought variables (soil moisture, evaporation, potential evaporation, temperature, and precipitation). Results showed Ada boosting was the most effective at representing and predicting flash drought events and was able to learn the climatological hotspots and some of the seasonality for flash droughts. However, the ML models tended to over rely on a few variables and were biased toward those variables. Additionally, case studies showed that the ML models struggled to capture the precise timing of flash drought events, resulting in a low skill score for all the examined ML models.
- 1 July 2025
- Published by American Meteorological Society in Artificial Intelligence for the Earth Systems
- Vol. 4 (3)
Evaluation of Flash Drought Identification with Machine Learning Techniques. Part I: Traditional Machine Learning Algorithms
Drought is an extreme event that can have a number of impacts on water resources and agricultural productivity. To mitigate the impacts, many studies have focused on improving drought predictions. As part of this, machine learning (ML) has emerged as a useful tool for drought identification and prediction, which has been shown to skillfully predict seasonal-scale droughts. In addition, a subset of drought, termed flash drought, has gained increased attention due to its rapid development and difficulty to predict. Studies focused on flash droughts have found a number of variables that accurately characterize their rapidly evolving conditions. However, while much work has been conducted to investigate flash droughts, limited work has been completed using ML techniques. This study investigated the ability of ML algorithms to represent and predict flash drought events via two parts. The first part focused on standard ML techniques such as random forests, Ada boosting, and support vector machines, while the second part focused on neural-network-based models. The ML models were trained on a set of key flash drought variables (soil moisture, evaporation, potential evaporation, temperature, and precipitation). Results showed Ada boosting was the most effective at representing and predicting flash drought events and was able to learn the climatological hotspots and some of the seasonality for flash droughts. However, the ML models tended to over rely on a few variables and were biased toward those variables. Additionally, case studies showed that the ML models struggled to capture the precise timing of flash drought events, resulting in a low skill score for all the examined ML models.
- 1 July 2025
- Published by American Meteorological Society in Artificial Intelligence for the Earth Systems
- Vol. 4 (3)
Evaluation of Flash Drought Identification with Machine Learning Techniques. Part II: Neural Network Algorithms
Flash droughts (FDs) describe the rapid onset of drought conditions and can have numerous impacts on agriculture and ecosystems due to rapid desiccation of the landscape. Recent studies into FDs have shown that the surface variables that drive these events include soil moisture, evapotranspiration, and potential evapotranspiration. However, studies that use machine learning (ML) to examine flash drought are still limited, despite the skill they have shown at identifying seasonal-scale droughts. This study is the second part in an investigation of FD representation and prediction using ML methods. Part I investigated traditional ML techniques, while this part investigated the ability of neural network–based methods to identify FD events. Key variables (soil moisture, evaporation, potential evaporation, temperature, and precipitation) were incorporated to train the ML models. Artificial neural networks (ANNs) struggled to identify FDs because they could not learn the surface interactions that characterize FD events. Convolutional U-networks were more capable of learning FD patterns but still overemphasized spatial patterns. Recurrent neural networks (RNNs), using a long short-term memory layer, most frequently had the highest skill score when predicting FD patterns and reduced much of the overprediction of FDs that occurred with the standard ML algorithms. RNNs could also recreate regions where FDs were more frequent as well as the seasonality climatology of FDs better than standard algorithms for some FD identification methods (but struggled more with the seasonality for other identification methods). However, the RNNs still struggled with the precise timing of FD events. Overall, RNNs showed some skill and promise in representing FDs on climatological time scales.
- 1 July 2025
- Published by American Meteorological Society in Artificial Intelligence for the Earth Systems
- Vol. 4 (3)
Evaluation of Flash Drought Identification with Machine Learning Techniques. Part II: Neural Network Algorithms
Flash droughts (FDs) describe the rapid onset of drought conditions and can have numerous impacts on agriculture and ecosystems due to rapid desiccation of the landscape. Recent studies into FDs have shown that the surface variables that drive these events include soil moisture, evapotranspiration, and potential evapotranspiration. However, studies that use machine learning (ML) to examine flash drought are still limited, despite the skill they have shown at identifying seasonal-scale droughts. This study is the second part in an investigation of FD representation and prediction using ML methods. Part I investigated traditional ML techniques, while this part investigated the ability of neural network–based methods to identify FD events. Key variables (soil moisture, evaporation, potential evaporation, temperature, and precipitation) were incorporated to train the ML models. Artificial neural networks (ANNs) struggled to identify FDs because they could not learn the surface interactions that characterize FD events. Convolutional U-networks were more capable of learning FD patterns but still overemphasized spatial patterns. Recurrent neural networks (RNNs), using a long short-term memory layer, most frequently had the highest skill score when predicting FD patterns and reduced much of the overprediction of FDs that occurred with the standard ML algorithms. RNNs could also recreate regions where FDs were more frequent as well as the seasonality climatology of FDs better than standard algorithms for some FD identification methods (but struggled more with the seasonality for other identification methods). However, the RNNs still struggled with the precise timing of FD events. Overall, RNNs showed some skill and promise in representing FDs on climatological time scales.
- 4 April 2025
- Published by Elsevier in Technology in Society
- Vol. 82
A socio-technical framework for assessing flash drought risks to key biodiversity areas: A scientists' warning
- 4 April 2025
- Published by Elsevier in Technology in Society
- Vol. 82
A socio-technical framework for assessing flash drought risks to key biodiversity areas: A scientists' warning
- Open Access
- 31 December 2022
- Published by Elsevier in Agricultural and Forest Meteorology
- Vol. 330
Analysis of the critical components of flash drought using the standardized evaporative stress ratio
- 31 December 2022
- Published by Elsevier in Agricultural and Forest Meteorology
- Vol. 330
Open AccessAnalysis of the critical components of flash drought using the standardized evaporative stress ratio
- Open Access
- 15 June 2022
- Published by Elsevier in SSRN Electronic Journal
Decomposing the Critical Components of Flash Drought Using the Standardized Evaporative Stress Ratio
Flash droughts develop rapidly (∼1 month timescale) and produce significant ecological, agricultural, and socioeconomical impacts. Recent advances in our understanding of flash droughts have resulted in methods to identify and quantify flash drought events. However, few studies have been done to isolate the individual rapid intensification and drought components of flash drought, which could further determine their causes, evolution, and predictability. This study utilized the standardized evaporative stress ratio (SESR) to quantify individual components of flash drought from 1979 – 2019, using evapotranspiration (ET) and potential evapotranspiration (PET) data from the North American Regional Reanalysis (NARR) dataset. The temporal change in SESR was utilized to quantify the rapid intensification component of flash drought. The drought component was also determined using SESR and compared to the United States Drought Monitor. The results showed that SESR was able to represent the spatial coverage of drought well for regions east of the Rocky Mountains. Furthermore, the rapid intensification component agreed well with previous flash drought studies, with the overall climatology of rapid intensification events showing similar hotspots to the flash drought climatology east of the Rocky Mountains. The rapid intensification climatology suggested areas west of the Rocky Mountains experience rapid drying more often than east of the Rocky Mountains.
- 15 June 2022
- Published by Elsevier in SSRN Electronic Journal
Open AccessDecomposing the Critical Components of Flash Drought Using the Standardized Evaporative Stress Ratio
Flash droughts develop rapidly (∼1 month timescale) and produce significant ecological, agricultural, and socioeconomical impacts. Recent advances in our understanding of flash droughts have resulted in methods to identify and quantify flash drought events. However, few studies have been done to isolate the individual rapid intensification and drought components of flash drought, which could further determine their causes, evolution, and predictability. This study utilized the standardized evaporative stress ratio (SESR) to quantify individual components of flash drought from 1979 – 2019, using evapotranspiration (ET) and potential evapotranspiration (PET) data from the North American Regional Reanalysis (NARR) dataset. The temporal change in SESR was utilized to quantify the rapid intensification component of flash drought. The drought component was also determined using SESR and compared to the United States Drought Monitor. The results showed that SESR was able to represent the spatial coverage of drought well for regions east of the Rocky Mountains. Furthermore, the rapid intensification component agreed well with previous flash drought studies, with the overall climatology of rapid intensification events showing similar hotspots to the flash drought climatology east of the Rocky Mountains. The rapid intensification climatology suggested areas west of the Rocky Mountains experience rapid drying more often than east of the Rocky Mountains.