3-month Lead Time Research Articles

Predicting compound agricultural drought and hot events using a Cascade Modeling framework combining Bayesian Model Averaging ensemble with Vine Copula (CaMBMAViC)

Compound Agricultural Drought and Hot Events (CADHEs) cause more disastrous impacts on water-food-energy-ecology security in comparison with individual drought or hot extremes. Reliable CADHEs predictions are therefore paramount to mitigate the potential risk associated with drought and hot events and their combinations. However, there is no prediction model with multi-predictand variables for reliably predicting CADHEs by considering the compounding influence of diverse confounders. In this study, we first employed a Cascade Modeling (CaM) framework to measure the cascading effects between agricultural droughts and hot events driven by the compounding influence of different confounders. Then, a new ensemble prediction model with multi-predictand variables using a CaM framework coupling Bayesian Model Averaging ensemble with Vine Copula, namely the CaMBMAViC model, was developed to simultaneously predict agricultural droughts, hot events, and CADHEs in the warm season with 1–3-month lead times in China, in which the three most important predictors were selected as the explanatory variables. For these selected typical years (e.g., 2006, 2013, and 2019, as the droughts and hot events in these years swept over most regions of China), the proposed CaMBMAViC model has provided reliable predictions for agricultural droughts, hot events, and CADHEs with 1–3-month lead times in the warm season over most areas of China. Two performance metrics, Kling-Gupta Efficiency (KGE) and Percent Bias (PBIAS), both demonstrated that this model yielded skillful predictions for agricultural droughts (KGE > 0.9 and PBIAS = [1.79%, 1.96%]), hot events (KGE > 0.86 and PBIAS = [2.23%, 2.72%]), and CADHEs (KGE > 0.83 and PBIAS = [–0.95%, 0.36%]) for most areas in China. These findings enhance our confidence in seasonal predictions of compound climate events and help us understand their future dynamic.

Agricultural Drought-Triggering for Anticipatory Action in Papua New Guinea

Throughout its history, Papua New Guinea (PNG) has faced recurrent agricultural droughts, imposing considerable strain on both livelihoods and the economy. Particularly severe droughts have been associated with El Niño climate patterns. During these episodes, PNG becomes especially vulnerable to extended periods of aridity and diminished precipitation. Historically, humanitarian assistance for these events has primarily focused on responding to emergencies after an agricultural drought has been declared and communities have already been impacted. Here, we developed a proactive agricultural drought-triggering method for anticipatory action (AA) in PNG to offer a more sustainable and cost-effective approach to address this hazard. Our AA uses weather forecasts and risk data to identify and implement mitigative actions before a disaster occurs. The research details a step-by-step guide from early warning to action implemented by the Food and Agricultural Organization of the United Nations and the Government of Papua New Guinea. This preemptive disaster risk management initiative integrates a combined drought index (CDI) with specific thresholds and tailored anticipatory actions based on crop calendars. Moreover, the developed CDI provides a 3-month lead time for implementing AA to reduce the impact of the agricultural drought. During the El Niño-induced drought event that began in 2023, the CDI was tested and the AA was piloted for the first time.

Short lead time standard precipitation index forecasting: Extreme learning machine and variational mode decomposition

Study region: Six regions in Algeria have been selected as follows: Ain Elhadjel, Msaad, Boussaada, Elkantara, M’sila and M’doukel.Study focus: This study focused on creating a novel hybrid VMD-ELM approach, established by combining the Variational Mode Decomposition (VMD) technique and the Extreme Learning Machine (ELM) algorithm as a preprocessing technique for predicting future droughts. The first 6 and 12-month SPI values 1, 2, and 3-month lead time values were estimated with the ELM algorithm. After that, meteorological variables and Standard Precipitation Index (SPI) values, divided into subcomponents with VMD, are presented to the ELM model, and a drought forecasting model is developed. Model performances were evaluated according to various visual and statistical criteria.New hydrological insights for the region: Soft computing techniques have become the preferred method for producing predictions due to their ability to minimize development time, require minimal input, and offer a relatively less complex approach when compared to dynamic or physical models. As a result of the analysis, it has been determined that the highest prediction accuracies are generally obtained in VMD-ELM models and SPI predictions with a 1-month lead time. The study outputs give important ideas to mite donors regarding water resource planning and climate change adaptation strategies in the study area and can be applied to other arid and semi-arid environments.

Estudio de teleconexión entre variables hidrológicas y climatológicas en una cuenca de cabecera del Rio Maipo para la aplicación de modelos de pronóstico

This study conducts a teleconnection analysis of the seasonal streamflow during the dry season (winter and summer) at the Olivares River basin, a headwater of the Maipo River basin, with traditional climate indices (Antarctic Oscillation, Niño1+2, and Niño3.4), new indices obtained from sea surface temperature (SST) anomaly spatial fields, and in situ hydrometeorological variables from the previous season to identify potential predictors for implementing seasonal streamflow forecast models in the study area. To illustrate the potential of the predictors identified, we fit multiple linear regression models (MLRM) for seasonal streamflow forecast for 0- and 3-month lead times. The forecasts are validated using the leave-1-year-out cross-validation (LOOCV) approach and performance metrics such as the Pearson correlation coefficient (R), BIAS, Nash-Sutcliffe efficiency (NSE), and continuous rank probability skill score (CRPSS). Results show a good performance of the forecast model for cross-validation with R and NSE values ranging from 0.55 to 0.95 and from 0.28 to 0.88 for 0- and 3-month lead times during the dry season. This early implementation provides good perspectives for implementing probabilistic seasonal streamflow forecasting models, which can provide a powerful output to develop robust water management strategies to tackle water scarcity in the study area.

CanStoc: A Hybrid Stochastic–GCM System for Monthly, Seasonal and Interannual Predictions

Beyond their deterministic predictability limits of ≈10 days and 6 months, the atmosphere and ocean become effectively stochastic. This has led to the development of stochastic models specifically for this macroweather regime. A particularly promising approach is based on the Fractional Energy Balance Equation (FEBE), an update of the classical Budyko–Sellers energy balance approach. The FEBE has scaling symmetries that imply long memories, and these are exploited in the Stochastic Seasonal and Interannual Prediction System (StocSIPS). Whereas classical long-range forecast systems are initial value problems based on spatial information, StocSIPS is a past value problem based on (long) series at each pixel. We show how to combine StocSIPS with a classical coupled GCM system (CanSIPS) into a hybrid system (CanStoc), the skill of which is better than either. We show that for one-month lead times, CanStoc’s skill is particularly enhanced over either CanSIPS or StocSIPS, whereas for 2–3-month lead times, CanSIPS provides little extra skill. As expected, the CanStoc skill is higher over ocean than over land with some seasonal dependence. From the classical point of view, CanStoc could be regarded as a post-processing technique. From the stochastic point of view, CanStoc could be regarded as a way of harnessing extra skill at the submonthly scales in which StocSIPS is not expected to apply.

Application of Hybrid ANN Techniques for Drought Forecasting in the Semi-Arid Region of India.

The intensity and frequency of diverse hydro-meteorological disasters viz., extreme droughts, severe floods, and cyclones have increasing trends due to unsustainable management of land and water resources, coupled with increasing industrialization, urbanization and climate change. This study focuses on the forecasting of drought using selected Artificial Neural Network (ANN)-based models to enable decision-makers to improve regional water management plans and disaster mitigation/reduction plans. Four ANN models were developed in this study, viz., one conventional ANN model and three hybrid ANN models: (a) Wavelet based-ANN (WANN), (b) Bootstrap based-ANN (BANN), and (c) Wavelet-Bootstrap based-ANN (WBANN). The Standardized Precipitation Evapotranspiration Index (SPEI), the best drought index identified for the study area, was used as a variable for drought forecasting. Three drought indices, such as SPEI-3, SPEI-6 and SPEI-12 respectively representing "short-term", "intermediate-term", and "long-term" drought conditions, were forecasted for 1-month to 3-month lead times for six weather stations over the study area. Both statistical and graphical indicators were considered to assess the performance of the developed models. For the hybrid wavelet model, the performance was evaluated for different vanishing moments of Daubechies wavelets and decomposition levels. The best-performing bootstrap-based model was further used for analysing the uncertainty associated with different drought forecasts. Among the models developed for drought forecasting for 1 to 3 months, the performances of the WANN and WBANN models are superior to the simple ANN and BANN models for the SPEI-3, SPEI-6, and SPEI-12 up to the 3-month lead time. The performance of the WANN and WBANN models is the best for SPEI-12 (MAE = 0.091-0.347, NSE = 0.873-0.982) followed by SPEI-6 (MAE = 0.258-0.593; NSE = 0.487-0.848) and SPEI-3 (MAE = 0.332-0.787, NSE = 0.196-0.825) for all the stations up to 3-month lead time. This finding is supported by the WBANN analyze uncertainties as narrower band width for SPEI-12 (0.240-0.898) as compared to SPEI-6 (0.402-1.62) and SPEI-3 (0.474-2.304). Therefore, the WBANN model is recommended for the early warning of drought events as it facilitates the uncertainty analysis of drought forecasting results.

Monthly streamflow forecasting by machine learning methods using dynamic weather prediction model outputs over Iran

Seasonal hydrological forecasts play a critical role in water resources management. The Copernicus Climate Change Service (C3S) data store provides open access to monthly hydrological forecasts for up to six-months. This study aims to evaluate, for the first time, 1- to 3-month runoff forecasts using the European Centre for Medium-Range Weather Forecasts (ECMWF) ensembles of precipitation, runoff, and temperature in 1981–2015 period over a total of 30 s-level basins in Iran. We adopted the 5th, 50th and 95th ECMWF ensemble quantiles for each variable that represent low, medium and high probability of occurrence, respectively. Pearson correlation analysis (Pca), Recursive Feature Elimination (RFE) via random forest (RF) model, and Bayesian Networks (BN) feature selection algorithms were used in order to reduce input variable dimension and select potential predictors to be fed to the machine learning models. Multiple Linear Regression (MLR), Artificial Neural Networks (ANN), Support Vector Regression (SVR), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) machine learning models were used with Repeated K-Fold cross validation (rK-Fold CV) while model efficiency was evaluated using modified Kling-Gupta efficiency coefficient (KGE’), Nash-Sutcliffe Efficiency coefficient (NSE), and Normalized Root Mean Square Error (NRMSE). Results of this study revealed that C3S runoff ensembles have the highest impact on forecast accuracy of streamflow, followed by precipitation and temperature. Overall, model performance yield a best-to-worst ranking of ANN, XGBoost, RF, MLR, and SVR with KGE’ values of 0.70, 0.68, 0.66, 0.57, and 0.41, respectively. The predictive performance of all models decreased with lead times beyond 1-month, where ANN and XGBoost outperformed other models with KGE’ of 0.65 for 2-month lead time and 0.60 for 3-month lead time. The three superior models of XGBoost, ANN, and RF, were employed with RFE and BN FSAs most frequently across Iran’s 30 s level basins in all lead times. Almost all models in the arid central region of Iran showed the lowest performance while highest skills were achieved in the western regions of Iran. Finally, for all models and over all regions, the model performance reduced by increase in lead-time.

Sources of skill in lake temperature, discharge and ice-off seasonal forecasting tools

Abstract. Despite high potential benefits, the development of seasonal forecasting tools in the water sector has been slower than in other sectors. Here we assess the skill of seasonal forecasting tools for lakes and reservoirs set up at four sites in Australia and Europe. These tools consist of coupled hydrological catchment and lake models forced with seasonal meteorological forecast ensembles to provide probabilistic predictions of seasonal anomalies in water discharge, temperature and ice-off. Successful implementation requires a rigorous assessment of the tools' predictive skill and an apportionment of the predictability between legacy effects and input forcing data. To this end, models were forced with two meteorological datasets from the European Centre for Medium-Range Weather Forecasts (ECMWF), the seasonal forecasting system, SEAS5, with 3-month lead times and the ERA5 reanalysis. Historical skill was assessed by comparing both model outputs, i.e. seasonal lake hindcasts (forced with SEAS5), and pseudo-observations (forced with ERA5). The skill of the seasonal lake hindcasts was generally low although higher than the reference hindcasts, i.e. pseudo-observations, at some sites for certain combinations of season and variable. The SEAS5 meteorological predictions showed less skill than the lake hindcasts. In fact, skilful lake hindcasts identified for selected seasons and variables were not always synchronous with skilful SEAS5 meteorological hindcasts, raising questions on the source of the predictability. A set of sensitivity analyses showed that most of the forecasting skill originates from legacy effects, although during winter and spring in Norway some skill was coming from SEAS5 over the 3-month target season. When SEAS5 hindcasts were skilful, additional predictive skill originates from the interaction between legacy and SEAS5 skill. We conclude that lake forecasts forced with an ensemble of boundary conditions resampled from historical meteorology are currently likely to yield higher-quality forecasts in most cases.

Seasonal forecasting skill for the High Mountain Asia region in the Goddard Earth Observing System

Abstract. Seasonal variability of the global hydrologic cycle directly impacts human activities, including hazard assessment and mitigation, agricultural decisions, and water resources management. This is particularly true across the High Mountain Asia (HMA) region, where availability of water resources can change depending on local seasonality of the hydrologic cycle. Forecasting the atmospheric states and surface conditions, including hydrometeorologically relevant variables, at subseasonal-to-seasonal (S2S) lead times of weeks to months is an area of active research and development. NASA's Goddard Earth Observing System (GEOS) S2S prediction system has been developed with this research goal in mind. Here, we benchmark the forecast skill of GEOS-S2S (version 2) hydrometeorological forecasts at 1–3-month lead times in the HMA region, including a portion of the Indian subcontinent, during the retrospective forecast period, 1981–2016. To assess forecast skill, we evaluate 2 m air temperature, total precipitation, fractional snow cover, snow water equivalent, surface soil moisture, and terrestrial water storage forecasts against the Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) and independent reanalysis data, satellite observations, and data fusion products. Anomaly correlation is highest when the forecasts are evaluated against MERRA-2 and particularly in variables with long memory in the climate system, likely due to the similar initial conditions and model architecture used in GEOS-S2S and MERRA-2. When compared to MERRA-2, results for the 1-month forecast skill range from an anomaly correlation of Ranom=0.18 for precipitation to Ranom=0.62 for soil moisture. Anomaly correlations are consistently lower when forecasts are evaluated against independent observations; results for the 1-month forecast skill range from Ranom=0.13 for snow water equivalent to Ranom=0.24 for fractional snow cover. We find that, generally, hydrometeorological forecast skill is dependent on the forecast lead time, the memory of the variable within the physical system, and the validation dataset used. Overall, these results benchmark the GEOS-S2S system's ability to forecast HMA hydrometeorology.

Projecting live fuel moisture content via deep learning

Background Live fuel moisture content (LFMC) is a key environmental indicator used to monitor for high wildfire risk conditions. Many statistical models have been proposed to predict LFMC from remotely sensed data; however, almost all these estimate current LFMC (nowcasting models). Accurate modelling of LFMC in advance (projection models) would provide wildfire managers with more timely information for assessing and preparing for wildfire risk. Aims The aim of this study was to investigate the potential for deep learning models to predict LFMC across the continental United States 3 months in advance. Method Temporal convolutional networks were trained and evaluated using a large database of field measured samples, as well as year-long time series of MODerate resolution Imaging Spectroradiometer (MODIS) reflectance data and Parameter-elevation Relationships on Independent Slopes Model (PRISM) meteorological data. Key results The proposed 3-month projection model achieved an accuracy (root mean squared error (RMSE) 27.52%; R2 0.47) close to that of the nowcasting model (RMSE 26.52%; R2 0.51). Conclusions The study is the first to predict LFMC with a 3-month lead-time, demonstrating the potential for deep learning models to make reliable LFMC projections. Implications These findings are beneficial for wildfire management and risk assessment, showing proof-of-concept for providing advance information useful to help mitigate the effect of catastrophic wildfires.

Combined Effect of the Tropical Indian Ocean and Tropical North Atlantic Sea Surface Temperature Anomaly on the Tibetan Plateau Precipitation Anomaly in Late Summer

Abstract Precipitation variability over the Tibetan Plateau (TP) depends largely on the atmospheric circulation pattern associated with remote oceanic forcing, while the contribution of sea surface temperature anomalies (SSTAs) in different ocean basins, especially the tropical North Atlantic (TNA), remains unclear. By using multisource data and atmospheric general circulation model, this study reveals the individual and combined effects of the Indian Ocean basin mode (IOBM) and TNA SSTA on the interannual variability of TP precipitation in late summer (August). During the positive phase of the IOBM, warm SSTAs in the Indian Ocean induce an anomalous anticyclone over the Bay of Bengal (BOBAC) via the Kelvin wave–induced Ekman divergence and a resulting positive precipitation anomaly over the southeastern TP. Simultaneously, an eastward-extending Kelvin wave triggered by the positive TNA SSTA overlaps with that caused by the IOBM, further strengthening the BOBAC. In addition, the Kelvin wave triggered by the TNA SSTA induces anomalous easterlies over the tropical Indo-Pacific, which contribute to the warm Indian Ocean SSTA and thus amplify the IOBM affecting TP precipitation. Moreover, the positive TNA SSTA generates a westward-extending Walker circulation anomaly that is responsible for the suppressed convection over the central Pacific, which in turn triggers a Rossby wave response and further strengthens the BOBAC. As a result, the positive precipitation anomaly over the southeastern TP is strengthened significantly. Particularly, considering the 2–3-month lead time of the IOBM and TNA SSTA, the tropical SSTA can be used as a predictor for the TP precipitation anomaly.

A framework of integrating heterogeneous data sources for monthly streamflow prediction using a state-of-the-art deep learning model

Deep learning has been widely used in hydrological prediction such as monthly streamflow and its performance is usually dependent on the abundance of training data. Even though the interest in using predictors from multiple data sources (e.g., streamflow observations, local meteorological data, and large-scale climate indexes) to train deep learning models for monthly streamflow prediction is growing, these predictors are usually selected from historical periods. Such approaches have limitations that the non-stationary future climate information is not included in the deep learning models. Climate models can provide non-stationary climate information for the future period, which may be useful for monthly streamflow prediction. Therefore, the objectives of this study are to (1) investigate the added value of using predictors derived from global climate models (GCMs) for monthly streamflow prediction based on a state-of-the-art deep learning model, and (2) propose a framework for integrating heterogeneous data sources for monthly streamflow prediction. The framework consists of five integral components: data collection, predictor combination, predictor selection, model construction, and results evaluation. In this study, a hybrid deep learning model combining Convolutional Neural Network and Gated Recurrent Unit was applied for six hydrological stations from mainstream and six stations from tributaries of the Yangtze River. Historical hydroclimate data and GCM hindcasts from 1982 to 2010 are used in monthly streamflow forecasts. Hindcasts are retrospective forecasts for many variables in the past, ideally conducted using the same model used for real-time forecasts. The results show that GCM hindcasts are useful predictors to improve the prediction accuracy for monthly streamflow predictions, especially for the 1- and 3-month lead times. Combining GCM hindcasts with either historical meteorological data or historical streamflow observations and meteorological data as predictors generally provides the best predictive performance. In addition, using large-scale climate indexes as ancillary information is able to improve the predictive performance at a lead time of 6 months. For lead times of 1, 3, and 6 months, the Kling‐Gupta efficiency (KGE) and the mean relative error (MRE)) metrics calculated based on the best-performing predictor combinations are satisfactory for hydrological stations in both mainstream and tributaries, with the median KGE being higher than 0.85 and 0.62, and the median MRE being approximately 20 % and 40 %, respectively, suggesting the monthly streamflow predictions are better for mainstream than for tributaries. Overall results show that (1) the inclusion of predicted information from GCMs can improve the performance for monthly streamflow prediction, and (2) the way of combining various heterogeneous data sources is crucial.

Decadal Variation of Predictability of the Indian Ocean Dipole during 1880–2017 Using an Ensemble Prediction System

Abstract In this study, we investigate both the decadal variation of the Indian Ocean dipole (IOD) prediction skill and possible sources of this decadal variation. We use an ensemble long-term retrospective forecast experiment covering 1880–2017 that utilizes the Community Earth System Model (CESM). We find that the decadal variation of the IOD prediction skill is significant and that it varies with the lead time. We also find that the decadal variation of the IOD prediction skill for the target season of boreal autumn determines that for all initial conditions, regardless of the lead months. For short lead times, the decadal variations of the IOD strength and of the IOD precursor in the initial month of July are the major factors influencing the IOD prediction skill. This occurs because the IOD events are in the developmental phase, and the stronger IOD signal in the initial conditions leads to better predictions. For long lead times, the decadal variation of remote forcing by El Niño–Southern Oscillation (ENSO) and the ENSO precursor signal in the IOD influence the IOD prediction skill more significantly than do the strengths of the ENSO or the IOD. In addition, the analysis also indicated that the period with a low ENSO–IOD relationship has low predictability, not only because the ENSO little influence on IOD but also because the model biasedly overestimates the ENSO–IOD relationship. Significance Statement The Indian Ocean dipole (IOD) has strong climatic effects, both around the Indian Ocean and globally, which have strong impacts on human life and economic development. It is important to be able to predict IOD events accurately to mitigate those impacts. Here, we conducted a 138-yr prediction experiment using a state-of-the-art climate model to confirm the existence of a decadal variation in IOD predictability and to identify factors that influence the IOD prediction skill. The most important factors that influence the decadal variation of IOD prediction skill differ for 3-month and 6-month lead times, and additional studies will be necessary to clarify the specific factors responsible for these differences.

Application of artificial intelligence models for prediction of groundwater level fluctuations: case study (Tehran-Karaj alluvial aquifer).

The nonlinear groundwater level fluctuations depend on the interaction of many factors such as evapotranspiration, precipitation, groundwater abstraction, and hydrogeological characteristics, making groundwater level prediction a complex task. Groundwater level changes are among the most critical issues in water resource management, which can be predicted to effectively provide management solutions to conserve renewable water resources. Understanding the aquifer status using numerical models is time-consuming and also is associated with inherent uncertainty; therefore, in recent decades, the application of artificial intelligence methods to predict water table fluctuations has significantly gained momentum. In this study, artificial neural network (ANN), fuzzy logic (FL), adaptive neuro-fuzzy inference system (ANFIS), and least square support vector machine (SVM) methods were utilized to predict groundwater level (GWL) with 1-, 2-, and 3-month lead time in Tehran-Karaj plain. Several input scenarios were developed considering groundwater levels, average temperature, total precipitation, total evapotranspiration, and average river flow on a monthly interval. The four error criteria, the correlation coefficient (R), root mean squared error (RMSE), Nash-Sutcliffe efficiency (NSE), and mean absolute error (MAE), were the basis to evaluate the models. Results showed that all the applied methods could provide acceptable GWL prediction, but the ANFIS was the most accurate. However, the ANFIS model showed slightly better performance by yielding R = 0.98 for the training stage and R = 0.98 for the testing stage in the P84 observation well and the second combination of inputs and 1-month lead time. The outcomes also revealed that all the approaches mentioned above could appropriately predict GWL for the leading time of 1 and 2months, but the models provided unsatisfactory results for a 3-month leading time.

Statistical Seasonal Forecasting of Winter and Spring PM2.5 Concentrations Over the Korean Peninsula.

Concentrations of fine particulate matter smaller than 2.5 μm in diameter (PM2.5) over the Korean Peninsula experience year-to-year variations due to interannual variation in climate conditions. This study develops a multiple linear regression model based on slowly varying boundary conditions to predict winter and spring PM2.5 concentrations at 1–3-month lead times. Nation-wide observations of Korea, which began in 2015, is extended back to 2005 using the local Seoul government’s observations, constructing a long-term dataset covering the 2005–2019 period. Using the forward selection stepwise regression approach, we identify sea surface temperature (SST), soil moisture, and 2-m air temperature as predictors for the model, while rejecting sea ice concentration and snow depth due to weak correlations with seasonal PM2.5 concentrations. For the wintertime (December–January–February, DJF), the model based on SSTs over the equatorial Atlantic and soil moisture over the eastern Europe along with the linear PM2.5 concentration trend generates a 3-month forecasts that shows a 0.69 correlation with observations. For the springtime (March–April–May, MAM), the accuracy of the model using SSTs over North Pacific and 2-m air temperature over East Asia increases to 0.75. Additionally, we find a linear relationship between the seasonal mean PM2.5 concentration and an extreme metric, i.e., seasonal number of high PM2.5 concentration days.Supplementary InformationThe online version contains supplementary material available at 10.1007/s13143-022-00275-4.

Support vector machine and data assimilation framework for Groundwater Level Forecasting using GRACE satellite data

Groundwater (GW) is a vital resource for human consumption, agriculture, environmental sustainability, and socio-economic development in different parts of the world. Besides, GW plays a crucial role in minimizing the impacts during extreme drought events. However, there is a fast decline in groundwater resources due to increased sectoral water demand compounded by reduced rainfall and rising temperature. Therefore, it is essential to develop appropriate tools to study spatio-temporal dynamics and predict groundwater levels to improve water resource management, especially during drought events. In this study, we applied machine learning algorithms based on support vector machines (SVMs), combined with data assimilation (DA) technique to predict the change in groundwater levels (CGWLs) at 1 to 3-month time scales for 46 GW wells located at the northeast United States. The in-situ climate variables and the Gravity Recovery and Climate Experiment (GRACE) mission-informed groundwater anomalies data (GWA) are used to develop the models. The results suggest that SVMs (SVM-DA) models forced with limited climate variables (i.e., precipitation, solar radiation, air temperature, infrared surface temperature) can forecast the CGWLs up to 3-month lead times at most of the locations. The addition of GRACE data as a forcing variable can improve the performance of SVMs at most of the stations, where a strong relationship exists between the CGWLs and the GWA. The SVM-DA model comparatively performed better than SVMs at most of the stations.

Rainfall variation over Sinai Peninsula and its teleconnection to El Niño sea surface temperature

This study aims at investigating the spatial and temporal variability of the seasonal rainfall over Sinai Peninsula, Egypt, relying on rainfall data taken from gridded data of four gauge stations for 35 years. Moreover, this study determines the teleconnection between the seasonal rainfall and equatorial Pacific sea surface temperature (El Niño SST) over El Arish and Wadi Watir. Due to non-stationary characteristics of Sinai rainfall, this study employs the Wavelet Principal Component Analysis (WPCA) technique. According to the spatial characteristics of January, February and March (JFM), and October, November and December (OND) rainfall seasons, Sinai Peninsula can be divided into two zones: northern zone along the coastal area of the Mediterranean, and central-southern zone. The WPC signals showed that the dominant frequency period of Sinai rainfall ranged 2–8 years. Using Wavelet Coherence (WC), the study found a strong teleconnection between the seasonal rainfall over El Arish and Wadi Watir as well and El Niño SST at a 3-month lead time. The study results will improve the forecasting skills of flash water events over Sinai Peninsula, particularly, the northern zone in order to take suitable precautions to eliminate their impacts.

Studies of the seasonal prediction of heavy late spring rainfall over southeastern China

The late spring rainfall may account for 15% of the annual total rainfall, which is crucial to early planting in southeastern China. A better understanding of the precipitation variations in the late spring and its predictability not only greatly increase our knowledge of related mechanisms, but it also benefits society and the economy. Four models participating in the North American Multi-Model Ensemble (NMME) were selected to study their abilities to forecast the late spring rainfall over southeastern China and the major sources of heavy rainfall from the perspective of the sea surface temperature (SST) field. We found that the models have better abilities to forecast the heavy rainfall over the middle and lower reaches of the Yangtze River region (MLYZR) with only a 1-month lead time, but they failed for a 3-month lead time since the occurrence of the heavy rainfall was inconsistent with the observations. The observations indicate that the warm SST anomalies in the tropical eastern Indian Ocean are vital to the simultaneously heavy rainfall in the MLYZR in May, but an El Niño event is not a necessary condition for determining the heavy rainfall over the MLYZR. The heavy rainfall over the MLYZR in May is always accompanied by warming of the northeastern Indian Ocean and of the northeastern South China Sea (NSCS) from April to May in the models and observations, respectively. In the models, El Niño events may promote the warming processes over the northeastern Indian Ocean, which leads to heavy rainfall in the MLYZR. However, in the real world, El Niño events are not the main reason for the warming of the NSCS, and further research on the causes of this warming is still needed.

Drought prediction using hybrid soft-computing methods for semi-arid region

Drought is one of the most significant natural disaster and prediction of drought is a key aspect in effective management of water resources and reducing the effect of a drought with preliminary studies plays significant role. In this study, we predicted one of the meteorological drought indices, the self-calibrated Palmer Drought Severity Index (sc-PDSI), values for Adana, Turkey. First, we used adaptive neuro fuzzy inference system (ANFIS) as a standalone technique to predict sc-PDSI. Second, we used empirical mode decomposition (EMD) as a pre-processing technique to decompose the sc-PDSI time series into the sub-series and applied ANFIS to each sub-series. Following the prediction, results are summed each other and final prediction of the hybrid EMD-ANFIS method is obtained. Within the scope of the study, 1, 3and 6-months lead time sc-PDSI values are predicted. We utilized the mean square error (MSE) and Nash–Sutcliffe efficiency coefficient (NSE) as performance indicators in order to perform statistical evaluation. For ANFIS, we obtained NSE = 0.52 and NSE = 0.17 for 3-month and 6-month lead times, respectively. Also, NSE values are obtained as 0.81 and 0.77 for the hybrid model in 3-month and 6-month lead time predictions, respectively. The results revealed that the hybrid EMD-ANFIS model outperforms the standalone ANFIS model. Also, the predicted and actual sc-PDSI series investigated according to the statistical distributions. At last, error histograms of both predicted and actual series are compared according to the Kolmogorov–Smirnov test and the p values are calculated. The results illustrated the predictions are statistically significant.

The Use of SST Anomaly to Predict Seasonal Rainfall during the Second Planting Period in the Tanoh Abee Irrigation Area, Aceh Besar

Irrigation in Tanoh Abee is used for agricultural activities especially during the second planting season during dry season. However, the availability of irrigation water is controlled by total rainfall received. An accurate prediction of rainfall, which traditionally used “keneunong” local wisdom, is urgently required. The objective of the study is to obtain the best predictor of seasonal rainfall based on the Pacific sea surface temperature (SST) anomaly and the monthly lead time of prediction. We employed monthly rainfall from six stations surrounding the study area and combined with principal component analysis to eliminate rainfall autocorrelation. Seasonal rainfall (quarterly average) was calculated from monthly data. The results showed that 1-month lead time strongly correlated to seasonal rainfall in Tanoh Abee (r<-0.7, α=5%) for the second planting period. On other hand, the 2-month and 3-month lead time were useful to predict seasonal rainfall in March-April-May (MAM) only. For April-May-June (AMJ) and May-June-July (MJJ), the correlation between SST anomaly and seasonal rainfall was weak. This finding indicated that the accuracy of prediction decreases with the longer lead time. Based on our analysis, coordinates of 170° E – 175° E; 5° N - 5° S in Niño 4 region have strongly correlated with seasonal rainfall in MAM, AMJ, and MJJ periods. Moreover, further research is necessary to combine any approaches that will improve our prediction skill for another 2- or 3-month lead time.