Drought Prediction Research Articles

Assessing Drought Patterns in Al-Baha: Implications for Water Resources and Climate Adaptation

Due to growing water demands and changing hydro-meteorological variables brought on by climate change, drought is becoming an increasingly serious climate concern. The Al-Baha region of Saudi Arabia is the subject of this study because it is susceptible to both agricultural and meteorological droughts. This study investigates how climate change affects patterns of drought in Al-Baha by analyzing four drought indices (Agricultural Standardized Precipitation Index (aSPI), the Standardized Precipitation Index (SPI), the Rainfall Deficiency Index (RDI), and the Effective Reconnaissance Drought Index (eRDI)) for the years 1991–2022. Analysis of rainfall data was carried out to classify drought events according to their duration, frequency, and severity. Results showed that severe droughts occurred in 2009, 2010, 2012, 2016, and 2022, with 2010 being the worst year. Results also indicated a notable decrease in precipitation, which has resulted in extended dry spells. Several indices indicate that this tendency has significant ramifications for agriculture, particularly in areas where farming is a major economic activity. In addition, the possible occurrence of hydrological drought was also observed based on the negative values for the Reservoir Storage Index (RSI) in Al-Baha. Projections for the future under two Representative Concentration Pathways (RCPs) showed notable variations in temperature and precipitation. Both the RCP4.5 (low emission) and the RCP8.5 (high emission) projection scenarios indicate that drought conditions will likely worsen further. Depending on the emission scenario, it is projected to show a temperature increase of 1–2 °C, whereas the variability in precipitation projections indicates significant uncertainty, with a reduction change in the range of 1.2–27% between 2050 and 2100. The findings highlight the urgent need for proactive adaptation strategies, effective water resource management, and the development of sophisticated drought prediction tools. Addressing these challenges is crucial for sustaining agriculture and managing water scarcity in Saudi Arabia in the face of increasing drought risk.

Prediction and assessment of meteorological drought in southwest China using long short-term memory model

Abstract Drought prediction is crucial for mitigating risks and designing measures to alleviate its impact. Machine learning models have been widely applied in the field of drought prediction in recent years. This study concentrated on predicting meteorological droughts in southwest China, a region prone to frequent and severe droughts, particularly in areas with sparse meteorological station coverage. The long short-term memory (LSTM) predictive model, which is a deep learning model, was constructed by calculating standardized precipitation evapotranspiration index (SPEI) values based on 144 weather station observations from 1980 to 2020. The 5-fold cross-validation method was used for the hyperparameter optimization of the model. The LSTM model underwent comprehensive assessment and validation through multiple methods. This included the use of several accuracy assessment indicators and a comparison of results. The comparison covered different drought characteristics among the LSTM predictive model, the benchmark random forest (RF) predictive model, the historical drought situations, and the calculated SPEI values based on observations from 144 weather stations. The results showed that the training results of the LSTM predictive model basically agreed with the SPEI values calculated from weather station observations. The model-predicted variation trend of SPEI values for 2020 was similar to the variation in SPEI values calculated based on weather station observations. On the test set, the coefficient of determination (R 2), the root mean square error, the explained variance score, the Nash–Sutcliffe efficiency, and the Kling–Gupta efficiency were 0.757, 0.210, 0.802, 0.761, and 0.212, respectively. The total consistency rate of the drought grade was 59.26%. The spatial correlation distribution of SPEI values between LSTM model prediction and calculation from meteorological stations in 2020 was more than 0.5 for most regions. The correlation coefficients exceeded 0.6 in western Tibet and Chengdu Plains. Compared to the RF model, the LSTM model excelled in all five performance evaluation metrics and demonstrated a higher overall consistency rate for drought categories. The Kruskal–Wallis test for both the LSTM and RF models all indicated no significant difference in the distributions between the predicted and observed data. Scatter plots revealed that the prediction accuracy for both models in 2020 was suboptimal, with the SPEI showing a comparatively narrow range of values. Nonetheless, the LSTM model significantly outperformed the RF model in terms of prediction accuracy. In summary, the LSTM model demonstrated good overall performance, accuracy, and applicability. It has the potential to enhance dynamic drought prediction in regions with complex terrain, diverse climatic factors, and sparse weather station networks.

Global Prediction of Flash Drought Using Machine Learning

AbstractFlash droughts are rapidly developing extreme weather events with sudden onset and quick intensification. Global prediction of flash droughts at sub‐seasonal time scales remains a great challenge. Current state‐of‐the‐art dynamic models subject to large errors and demonstrate low skills in global flash drought prediction. Here, we develop a machine learning‐based framework that uses meteorological forecasts as inputs to predict global root‐zone soil moisture and flash droughts from 1 day to 2 week lead times. The results indicate that 33% and 24% global flash drought onset and termination events can be correctly predicted by machine learning at 7 day lead time, versus 19% and 11% fractions by state‐of‐the‐art dynamic model. The developed machine learning model demonstrates substantial improvements over dynamic model in global soil moisture prediction, and thus enhances global flash drought forecasting skills in space and time. The presented framework may benefit global flash drought prediction and early warning at sub‐seasonal scales.

Dynamical systems-inspired machine learning methods for drought prediction

Dynamical systems-inspired machine learning methods for drought prediction

Evaluating and Predicting Meteorological Drought Using Different Climate Reanalysis Datasets over New South Wales, Australia

AbstractDroughts are one of the most disastrous natural hazards, primarily due to their persistence and spatial distribution. Drought prediction is one of the key challenges for effective drought management and to do so, studies often involve the use of station-based data which are effective only in regions with high-gauge density. Therefore, there is growing interest in the use of interpolated climatic grids to predict droughts. In recent decades, drought conditions have been aggravated by climate change and for that reason the use of climatic variables is important to accurately predict droughts. The analysis of any aspect of drought can be affected by the choice of data and drought index. Therefore, this study aims to identify the most suitable dataset and drought index for the New South Wales (NSW) region of Australia. The present study evaluates various precipitation datasets (Climate Research Unit (CRU), ERA-5, and Scientific Information for Land Owners (SILO)) and their corresponding variations on the Standardised Precipitation Index (SPI) at different time scales. Based on the findings, CRU was used to predict meteorological drought using machine learning techniques. The different machine learning models are Support Vector Regression, Random Forest and Artificial Neural Networks. The results suggest SVM to be the best performing model among these models for predicting SPI at short time scales (1 month and 3 month) and ANN to be the best performing model for long-term scales (6 months and 12 months). Such findings depict the capabilities of different models in examining drought characteristics and confirming the use of interpolated climatic grids thereby assisting in regional drought management.

Hydro-meteorological drought predictions and trend analysis for ungauged watersheds in the Upper Blue Nile basin, Ethiopia, under future climate change impact scenarios

Hydro-meteorological drought predictions and trend analysis for ungauged watersheds in the Upper Blue Nile basin, Ethiopia, under future climate change impact scenarios

How Does the East Siberian Sea Ice Affect the June Drought Over Northwest China After 2000?

AbstractChanges in Arctic sea ice have exerted remarkably effects on the Eurasian climates, but it is unclear whether Arctic sea ice also contributes to Northwest China's ongoing summer drought. This study investigates the influence of the interannual variability of Arctic sea ice on the June drought in Northwest China from 1979 to 2021. It reveals that the early‐autumn sea ice in the East Siberian Sea is correlated with drought conditions in June in Northwest China, with a more pronounced connection during the period of 2000/2001–2020/2021 (P2) compared to 1979/1980–1999/2000 (P1). Mitigated drought in Northwest China is associated with anomalously high sea ice concentration (SIC) in the East Siberian Sea. Further analysis suggests that the strengthened link may be due to greater SIC variability in the East Siberian Sea during P2 than P1. In P2, positive early‐autumn SIC anomaly is linked to anomalous northeasterly winds, promoting drier soil and widespread cooling in the East European Plain. This dry soil signal may persist into the ensuing spring and early summer, inducing an anticyclonic circulation anomaly over Siberia, which could facilitate the water vapor convergence in Northwest China, thereby enhancing humidity conditions in the region. The insights from this study could offer valuable information for improved prediction of droughts in Northwest China.

Multi-scale drought variability over West Africa and the associated large-scale circulation patterns

This study addresses the critical research gap in understanding regional drought dynamics in West Africa (WA) using advanced multivariate wavelet coherence (MWC) techniques, revealing critical insights into the complex interplay between large-scale climate indices and regional drought patterns. Utilizing the Standardized Precipitation Evapotranspiration Index (SPEI) and self-calibrating Palmer Drought Severity Index (scPDSI), we examined drought characteristics across WA from 1950 to 2018. Our analysis revealed significant drying trends across all seasons, with the Arid zone experiencing the most severe and prolonged drought (158 months) from August 1981 to September 1994, affecting 79.77% of the area. The entire WA region faced its most extensive drought during this period, impacting over 60% of the study area. MWC analysis demonstrated enhanced drought predictability when combining climate indices, particularly the Southern Oscillation Index with the Atlantic Multidecadal Oscillation, yielding high Average Wavelet Coherence values of 0.52 (SPEI) and 0.53 (scPDSI), with substantial Percentage Area of Significant Coherence of 40.19% and 43.68%, respectively. These findings highlight the crucial role of oceanic-atmospheric interactions in modulating drought conditions across WA. Our results provide valuable insights for improving drought forecasting and management strategies in the region, emphasizing the need for integrated approaches that consider multiple climate indices and their combined effects on drought dynamics.

A Framework for Monitoring the Effectiveness of Ecosystem-Based Adaptation Strategies Using Internet of Things and Machine Learning Techniques

Climate change poses a threat to the global ecosystem. Many countries adopt various approaches, including ecosystem-based adaptation (EbA), to address this problem. However, the assessment of the effectiveness of the EbA interventions is conducted manually, is resource-intensive, and is focused on short-term outputs. These limitations underscore a critical gap: the need for a comprehensive, automated system that enables long-term monitoring and predictive analysis. This study aimed to address this gap by developing an innovative framework that integrates Internet of Things (IoT) devices and machine learning (ML) algorithms to continuously monitor weather, hydrological, environmental, and other variables. We conducted a thorough analysis to design an appropriate framework. In addition, to obtain the relevant information and data, we conducted interviews with the local community and collected secondary data from various sources. The proposed framework consists of five layers: (i) EbA interventions; (ii) IoT-based key performance indicators (KPI) for monitoring and evaluation (M&E); (iii) primary data collection; (iv) data storage; and (v) application. As a proof of concept, we developed a system that supports early flood and drought alerts while simultaneously providing long-term evaluations of the effectiveness of EbA strategies. The developed system consists of IoT devices and a web application integrated with machine learning (ML). We set up and tested the IoT devices before deploying them in the study area. The devices capture data for two primary purposes: (1) short-term: flood detection and alerting, and (2) long-term: drought prediction and evaluation of EbA effectiveness through continuous data analysis. This research represents a significant advancement in the automation and long-term assessment of climate adaptation measures, offering a scalable and effective solution to disaster risk reduction.

Machine‐Learning Based Multi‐Layer Soil Moisture Forecasts—An Application Case Study of the Montana 2017 Flash Drought

AbstractSoil moisture (SM) is an essential climate variable, governing land‐atmosphere interactions, runoff generation, and vegetation growth and productivity. Timely forecasts of SM spatial distribution and vertical profiles are needed for early detection and prediction of potential droughts. However, previous studies have primarily concentrated on historical or near real‐time soil moisture mapping, with less effort devoted to the development and integration of soil moisture forecast components within drought assessment systems. A satellite‐driven machine‐learning approach was developed in this study to build complex relationships between diversified predictor data sets and in situ multi‐layer SM measurements from the Montana Mesonet, a regionally dense environmental station network in the US upper Missouri and Columbia basins. The resulting 30‐m daily SM predictions showed strong performance against in situ SM measurements from 4‐, 8‐ and 20‐inch soil layers, and with 1‐ to 2‐week forecast lead times (R > 0.91; RMSE ≤ 0.047 cm3/cm3). The machine‐learning model was subsequently applied to the entire Montana region, and the SM deficit forecasts with both 1‐ and 2‐week lead times successfully depicted onset, progression, and termination phases of the 2017 Montana flash drought, which was not effectively identified from prevailing operational systems. The resulting system is capable of delineating local scale SM heterogeneity, and could be extended to predict other critical water cycle variables, potentially enhancing future drought forecasts through multivariate assessments and benefiting water resource management, agricultural practices, and the provision of ecosystem services.

LSTM Model Integrated Remote Sensing Data for Drought Prediction: A Study on Climate Change Impacts on Water Availability in the Arid Region

Climate change is one of the trending terms in the world nowadays due to its profound impact on human health and activity. Extreme drought events and desertification are some of the results of climate change. This study utilized the power of AI tools by using the long short-term memory (LSTM) model to predict the drought index for Anbar Province, Iraq. The data from the standardized precipitation evapotranspiration index (SPEI) for 118 years have been used for the current study. The proposed model employed seven different optimizers to enhance the prediction performance. Based on different performance indicators, the results show that the RMSprop and Adamax optimizers achieved the highest accuracy (90.93% and 90.61%, respectively). Additionally, the models forecasted the next 40 years of the SPEI for the study area, where all the models showed an upward trend in the SPEI. In contrast, the best models expected no increase in the severity of drought. This research highlights the vital role of machine learning models and remote sensing in drought forecasting and the significance of these applications by providing accurate climate data for better water resources management, especially in arid regions like that of Anbar province.

An enhanced Standardized Precipitation–Evapotranspiration Index (SPEI) drought-monitoring method integrating land surface characteristics

Abstract. Atmospheric evaporative demand is a key metric for monitoring agricultural drought. Existing ways of estimating evaporative demand in drought indices do not faithfully represent the constraints imposed by land surface characteristics and become less accurate over nonuniform land surfaces. This study proposes incorporating surface vegetation characteristics, such as vegetation dynamics data, aerodynamic parameters, and physiological parameters, into existing potential-evapotranspiration (PET) methods. This approach is implemented across the continental United States (CONUS) for the period from 1981–2017 and is tested using a recently developed drought index, the Standardized Precipitation–Evapotranspiration Index (SPEI). We show that activating realistic maximum surface conductance and aerodynamic conductance could improve the prediction of soil moisture dynamics and drought impacts by 29 %–41 % on average compared to more simple, widely used methods. We also demonstrate that this is especially effective in forests and humid regions, with improvements of 86 %–89 %. Our approach only requires a minimal amount of ancillary data while allowing for both historical reconstruction and real-time drought forecasting. This offers a physically meaningful yet easy-to-implement way to account for vegetation control in drought indices.

Deep hybridnet for drought prediction based on large-scale climate indices and local meteorological conditions

Deep hybridnet for drought prediction based on large-scale climate indices and local meteorological conditions

Modelling drought in South Africa: meteorological insights and predictive parameters

South Africa has grappled with recurring drought scenarios for over two decades, leading to substantial economic losses. Droughts in the Western Cape between 2015 and 2018, especially in Cape Town was declared a national disaster, resulting in the strict water rationing and the “day zero” effect. This study presents a set of simulations for predicting drought over South Africa using Artificial Neural Network (ANN), using Standard Precipitation Index (SPI) as the drought indicator in line with the recommendations of the World Meteorological Organization (WMO). Furthermore, different meteorological variables and an aerosol parameter were used to develop the drought set in four distinct locations in South Africa for a 21-year period. That data used include relative humidity (rh), temperature (tp), soil wetness (sw), evapotranspiration (et), evaporation (ev) sea surface temperature (st), and aerosol optical depth (aa). The obtained R2 values for SPI3 ranged from 0.49 to 0.84 and from 0.22 to 0.84 for SPI6 at Spring Bok, Umtata 0.83 to 0.95 for SPI3, and 0.61 to 0.87 for SPI6; Cape Town displayed R2 values from 0.78 to 0.94 for SPI3 and 0.57 to 0.95 for SPI6, while Upington had 0.77–0.95 for SPI3, and 0.78–0.92 for SPI6. These findings underscore the significance of evapotranspiration (et) as a pivotal parameter in drought simulation. Additionally, the predictive accuracy of these parameter combinations varied distinctly across different locations, even for the same set of parameters. This implies that there is no single universal scheme for drought prediction. Hence, the results are important for simulating future drought scenarios at different parts of South Africa. Finally, this study shows that ANN is an effective tool that can be utilized for drought studies and simulations.

Investigating Hydrological Drought Characteristics in Northeastern Thailand in CMIP5 Climate Change Scenarios

In this study, we analyzed the predictions of hydrological droughts in the Lam Chiang Kri Watershed (LCKW) by using the Soil and Water Assessment Tool (SWAT) and streamflow data for 2010–2021. The objective was to assess the streamflow drought index (SDI) for 5-, 10-, 25-, and 50-year return periods (RPs) in 2029 and 2039 in two representative concentration pathway (RCP) scenarios: the moderate climate change scenario (RCP 4.5) and the high-emission scenario (RCP 8.5). The SWAT model showed high accuracy (R2 = 0.82, NSE = 0.78). In RCP4.5, streamflow is projected to increase by 34.74% for 2029 and 18.74% for 2039, while in RCP8.5, a 37.06% decrease is expected for 2029 and 55.84% for 2039. A historical analysis indicated that there were frequent short-term droughts according to SDI-3 (3-month-period index), particularly from 2014 to 2015 and 2020 to 2021, and severe droughts according to SDI-6 (6-month-period index) in 2015 and 2020. The RCP8.5 projections indicate worsening drought conditions, with critical periods from April to June. A wavelet analysis showed that there is a significant risk of severe hydrological drought in the LCKW. Drought characteristic analysis indicated that high-intensity events occur with low frequency in the 50-year RP. Conversely, high-frequency droughts with lower intensity are observed in RPs of less than 50 years. The results of this study highlight an increase in severe drought risk in high emission scenarios, emphasizing the need for water management.

A global flash drought inventory based on soil moisture volatility

Flash droughts, characterized by rapid onset and development, present significant challenges to agriculture and climate mitigation strategies. Operational drought monitoring systems, based on precipitation, soil moisture deficits, or temperature anomalies, often fall short in timely detection of these events, underscoring the need for customized identification and monitoring indices that account for the rapidity of flash drought onset. Recognizing this need, this paper introduces a global flash drought inventory from 1990 to 2021 derived using the Soil Moisture Volatility Index (SMVI). Our work expands the application of the SMVI methodology, previously focused on the United States, to a global scale, providing a tool for understanding and predicting these rapidly developing phenomena. The dataset encompasses detailed event characteristics, including onset, duration, and severity, across diverse climate zones. By integrating atmospheric variables through their impact on soil moisture, the inventory offers a platform for analyzing the drivers and impacts of flash droughts, and serves as a large, consistent dataset for use in training and evaluating flash drought prediction models.

Retraction Note: Drought prediction based on SPI and SPEI with varying timescales using LSTM recurrent neural network

Retraction Note: Drought prediction based on SPI and SPEI with varying timescales using LSTM recurrent neural network

Predicting agricultural and meteorological droughts using Holt Winter Conventional 2D-Long Short-Term Memory (HW-Conv2DLSTM).

Drought is an extended shortage of rainfall resulting in water scarcity and affecting a region's social and economic conditions through environmental deterioration. Its adverse environmental effects can be minimised by timely prediction. Drought detection uses only ground observation stations, but satellite-based supervision scans huge land mass stretches and offers highly effective monitoring. This paper puts forward a novel drought monitoring system using satellite imagery by considering the effects of droughts that devastated agriculture in Thanjavur district, Tamil Nadu, between 2000 and 2022. The proposed method uses Holt Winter Conventional 2D-Long Short-Term Memory (HW-Conv2DLSTM) to forecast meteorological and agricultural droughts. It employs Climate Hazards Group InfraRed Precipitation with Station (CHIRPS) data precipitation index datasets, MODIS 11A1 temperature index, and MODIS 13Q1 vegetation index. It extracts the time series data from satellite images using trend and seasonal patterns and smoothens them using Holt Winter alpha, beta, and gamma parameters. Finally, an effective drought prediction procedure is developed using Conv2D-LSTM to calculate the spatiotemporal correlation amongst drought indices. The HW-Conv2DLSTM offers a better R2 value of 0.97. It holds promise as an effective computer-assisted strategy to predict droughts and maintain agricultural productivity, which is vital to feed the ever-increasing human population.

Enhanced hydrological drought prediction in the Gediz Basin: integrating meteorological drought via hybrid wavelet-machine learning-random oversampling models using

ABSTRACT In study, meteorological drought ​​was used to estimate the potential hydrological drought that may occur in the Gediz Basin of Turkey. For this purpose, the most effective stream flow gauging station was determined by looking at the correlation values ​​between the meteorological data obtained from the Uşak meteorological station. SPEI values ​​for meteorological drought and SRI values ​​for hydrological drought are calculated for 3-, 6-, 9-, and 12-month periods. Correlation matrices were created between meteorological drought inputs from SPEI(t) to SPEI(t-12) and SRI(t) for use in hydrological drought models for 3-, 6-, 9- and 12-month periods. ML models were developed considering correlation matrices and it was seen that ML model results were not sufficient. For this reason, W-ML models were developed by applying DWT and Optuna hyperparameter analysis. It has been observed that the performance of W-ML models increases. Random oversampling (ROS), which has never been used in drought modeling, was then applied to W-ML models. W-ML-ROS model obtained an R2 value of 0.999 for testing set in 12-month period. Similarly, R2 values ​​for SRI3, SRI6 and SRI9 were obtained as 0.893, 0.851, and 0.940, respectively. Results showed that W-ML-ROS hybrid models can be used to predict hydrological drought from meteorological drought.

Drought prediction in Jilin Province based on deep learning and spatio-temporal sequence modeling

Jilin Province, a key agricultural hub in Northeast China, has long been impacted by climate change, with drought disasters significantly affecting its agricultural output and ecological environment. Accurate drought prediction is essential for the effective utilization of water resources and agricultural production. This study proposes a novel drought prediction model that utilizes the SSA-VMD (Sparrow Search Algorithm Optimized Variational Mode Decomposition) technique to decompose meteorological data, followed by the reconstruction of the decomposed components using four entropy algorithms, including approximate entropy. The model integrates ARIMA (AutoRegressive Integrated Moving Average) and BiLSTM (Bidirectional Long Short-Term Memory network) for forecasting the reconstructed components, subsequently combining their outputs. In terms of spatio-temporal data, the study employs prediction models including the spatio-temporal cube, spatio-temporal hotspot analysis integrated with empirical kriging, and local outlier analysis to examine spatial distribution. The model’s predictive performance is validated from three perspectives: statistical characteristics of the indicators, comparison between predicted and observed values through prediction curve plots, and box plots. The results demonstrate that the combined SSA-VMD-ARIMA-BiLSTM model significantly enhances prediction accuracy compared to single models, as exemplified by its application in Changchun City. The model achieved an R2 of 0.938 and a root mean square error (RMSE) of 0.047 in drought prediction, outperforming the single ARIMA model (R2: 0.636, RMSE: 0.709) and the BiLSTM model (R2: 0.514, RMSE: 0.901). Additionally, across the entire province, the model’s R2, MAE, and RMSE are 0.82, 0.15, and 0.083, respectively, suggesting that the model exhibits not only high prediction accuracy but also a degree of generalizability. Furthermore, the results from the spatio-temporal cube, spatio-temporal hotspot analysis, and local outlier analysis demonstrate the method’s high accuracy and stability in predicting both short-term and long-term droughts. Particularly in short-term drought prediction, the model effectively captures the spatio-temporal distribution characteristics of short-term meteorological droughts. This study offers new methodological support for enhancing the early warning capabilities of drought risk in Jilin Province, providing a robust foundation for addressing the challenges posed by climate change. The findings not only address certain shortcomings in current drought prediction research but also introduce new methodologies and perspectives for future studies.