Evaluation of performance of drought prediction in Indonesia based on TRMM and MERRA-2 using machine learning methods

Characterizing drought prediction with deep learning: A literature review

Drought prediction is a complex phenomenon that impacts human activities and the environment. For this reason, predicting its behavior is crucial to mitigating such effects. Deep learning techniques are emerging as a powerful tool for this task. The main goal of this work is to review the state-of-the-art for characterizing the deep learning techniques used in the drought prediction task. The results suggest that the most widely used climate indexes were the Standardized Precipitation Index (SPI) and the Standardized Precipitation Evapotranspiration Index (SPEI). Regarding the multispectral index, the Normalized Difference Vegetation Index (NDVI) is the indicator most utilized. On the other hand, countries with a higher production of scientific knowledge in this area are located in Asia and Oceania; meanwhile, America and Africa are the regions with few publications. Concerning deep learning methods, the Long-Short Term Memory network (LSTM) is the algorithm most implemented for this task, either implemented canonically or together with other deep learning techniques (hybrid methods). In conclusion, this review reveals a need for more scientific knowledge about drought prediction using multispectral indices and deep learning techniques in America and Africa; therefore, it is an opportunity to characterize the phenomenon in developing countries.

Fusion-based approach for hydrometeorological drought modeling: a regional investigation for Iran

The objective of this study was to model a new drought index called the Fusion-based Hydrological Meteorological Drought Index (FHMDI) to simultaneously monitor hydrological and meteorological drought. Aiming to estimate drought more accurately, local measurements were classified into various clusters using the AGNES clustering algorithm. Four single artificial intelligence (SAI) models-namely, Gaussian Process Regression (GPR), Ensemble, Feedforward Neural Networks (FNN), and Support Vector Regression (SVR)-were developed for each cluster. To promote the results of single of products and models, four fusion-based approaches, namely, Wavelet-Based (WB), Weighted Majority Voting (WMV), Extended Kalman Filter (EKF), and Entropy Weight (EW) methods, were used to estimate FHMDI in different time scales, precipitation, and runoff. The performance of single and combined products and models was assessed through statistical error metrics, such as Kling-Gupta efficiency (KGE), Mean Bias Error (MBE), and Normalized Root Mean Square Error (NRMSE). The performance of the proposed methodology was tested over 24 main river basins in Iran. The validation results of the FHMDI (the compliance of the index with the pre-existing drought index) revealed that it accurately identified drought conditions. The results indicated that individual products performed well in some river basins, while fusion-based models improved dataset accuracy more compared to local measurements. The WMV with the highest accuracy (lowest NRMSE) had a good performance in 60% of the cases compared to all other products and fusion-based models. WMV also showed higher efficiency in 100% of the cases than all other fusion-based and SAI models for simultaneous hydrological and meteorological drought estimation. In light of these findings, we recommend the use of fusion-based approach to improve drought modeling.

Merging Satellite and Gauge Rainfalls for Flood Forecasting of Two Catchments Under Different Climate Conditions

As satellite rainfall data has the advantages of wide spatial coverage and high spatial and temporal resolution, it is an important means to solve the problem of flood forecasting in ungauged basins (PUB). In this paper, two catchments under different conditions, Xin’an River Basin and Wuding River Basin, were selected as the representatives of humid and arid regions, respectively, and four kinds of satellite rainfall data of TRMM 3B42RT, TRMM 3B42V7, GPM IMERG Early, and GPM IMERG Late were selected to evaluate the monitoring accuracy of rainfall processes in the two catchments on hourly scale. Then, these satellite rainfall data were respectively integrated with the gauged data. HEC-HMS (The Hydrologic Engineering Center's-Hydrologic Modeling System) model was calibrated and validated to simulate flood events in the two catchments. Then, improvement effect of the rainfall merging on flood forecasting was evaluated. According to the research results, in most cases, the Nash–Sutcliffe efficiency coefficients of the simulated streamflow from initial TRMM (Tropical Rainfall Measuring Mission) and GPM (Global Precipitation Measurement) satellite rainfall data were negative at the two catchments. By merging gauge and TRMM rainfall, the Nash–Sutcliffe efficiency coefficient is mostly around 0.7, and the correlation coefficient is as high as 0.9 for streamflow simulation in the Xin'an River basin. For the streamflow simulated by merging gauge and GPM rainfall in Wuding River basin, the Nash–Sutcliffe efficiency coefficient is about 0.8, and the correlation coefficient is more than 0.9, which indicate good flood forecasting accuracy. Generally, higher performance statistics were obtained in the Xin'an River Basin than the Wuding River Basin. Compared with the streamflow simulated by the initial satellite rainfalls, significant improvement was obtained by the merged rainfall data, which indicates a good prospect for application of satellite rainfall in hydrological forecasting. In the future, it is necessary to further improve the monitoring accuracy of satellite rainfall products and to develop the method of merging multi-source rainfall data, so as to better applications in PUB and other hydrological researches.

Perception of weather and seasonal drought forecasts and its impact on livelihood in East Nusa Tenggara, Indonesia

A cross-sectional study was conducted in 2018 to assess the perception of households on drought forecasts and its impact on crop and livestock losses. A total of 300 households from seven districts in East Nusa Tenggara Indonesia were considered. The study indicated that the majority of the households are poor families with low education background. They sold poultry for income generation during drought events. The survey revealed that only small percentage of the households usied forecast to support their livelihood management. The statistical test confirmed that the use of forecast did not necessarily impacted the crop loss. However, the crops were significantly affected by the response to drought forecast. Households that changed their agricultural practice experienced significantly different losses than households that did not do anything differently to their crops. The households argued that the accuracy of the forecasts issued by the government was very low. Therefore, it is recommended that policymakers and government authorities provide more accurate forecasts and a better strategy to increase household awareness of using drought forecasts.