This repository contains codes for the paper: Foroumandi, E., K. Gavahi, and H. Moradkhani (2024), Generative Adversarial Network for Real-time Flash Drought Monitoring: A Deep Learning Study, Water Resources Research, Accepted
Abstract: Droughts are among the most devastating natural hazards, occurring in all regions with different climate conditions. The impacts of droughts result in significant damages annually around the world. While drought is generally described as a slow-developing hazardous event, a rapidly developing type of drought, the so-called flash drought has been revealed by recent studies. The rapid onset and strong intensity of flash droughts require accurate real-time monitoring. Addressing this issue, a Generative Adversarial Network (GAN) is developed in this study to monitor flash droughts over the Contiguous United States (CONUS). GAN contains two models: 1) discriminator and 2) generator. The developed architecture in this study employs a Markovian discriminator, which emphasizes the spatial dependencies, with a modified U-Net generator, tuned for optimal performance. To determine the best loss function for the generator, four different networks are developed with different loss functions, including Mean Absolute Error (MAE), adversarial loss, a combination of adversarial loss with Mean Square Error (MSE), and a combination of adversarial loss with MAE. Utilizing daily datasets collected from NLDAS-2 and Standardized Soil Moisture Index (SSI) maps, the network is trained for real-time daily SSI monitoring. Comparative assessments reveal the proposed GAN’s superior ability to replicate SSI values over U-Net and Naïve models. Evaluation metrics further underscore that the developed GAN successfully identifies both fine- and coarse-scale spatial drought patterns and abrupt changes in the SSI temporal patterns that is important for flash drought identification.
This repository contains codes for the paper: Gavahi, K., E. Foroumandi, and H. Moradkhani (2023), A deep learning-based framework for multi-source precipitation fusion, Remote Sensing of Environment, doi:10.1016/j.rse.2023.113723
Abstract: Accurate quantitative precipitation estimation (QPE) is essential for various applications, including land surface modeling, flood forecasting, drought monitoring and prediction. In situ precipitation datasets, remote sensing-based estimations, and reanalysis products have heterogeneous uncertainty. Numerous models have been developed to merge precipitation estimations from different sources to improve the accuracy of QPE. However, many of these attempts are mainly focused on spatial or temporal correlations between various remote sensing sources and/or gauge data separately, and thus, the developed model cannot fully capture the inherent spatiotemporal dependencies that could potentially improve the precipitation estimations. In this study, we developed a general framework that can simultaneously merge and downscale multiple user-defined precipitation products by using rain gauge observations as target values. A novel deep learning-based convolutional neural network architecture, namely, the precipitation data fusion network (PDFN), that combines multiple layers of 3D-CNN and ConvLSTM was developed to fully exploit the spatial and temporal patterns of precipitation. This architecture benefits from techniques such as batch normalization, data augmentation schemes, and dropout layers to avoid overfitting and address skewed class proportions due to the highly imbalanced nature of the precipitation datasets. The results showed that the fused daily product remarkably improved the mean square error (MSE) and Pearson correlation coefficient (PCC) by 35% and 16%, respectively, compared to the best-performing product.
This repository contains codes for the paper: Gavahi, K., P. Abbaszadeh, and H. Moradkhani (2021), DeepYield: A combined convolutional neural network with long short-term memory for crop yield forecasting, Expert Systems with Applications, doi: 10.1016/j.eswa.2021.115511
Abstract: Crop yield forecasting is of great importance to crop market planning, crop insurance, harvest management, and optimal nutrient management. Commonly used approaches for crop prediction include but are not limited to conducting extensive manual surveys or using data from remote sensing. Considering the increasing amount of data provided by remote sensing imagery, this approach is becoming increasingly important for the task of crop yield forecasting and there is a need for more sophisticated approaches to extract the inherent spatiotemporal patterns of these data. Although considerable progress has been made in this field by using Deep Learning (DL) methods such as Convolutional Neural Networks (CNN), no study before has investigated the use of Convolutional Long Short-Term Memory (ConvLSTM) for crop yield forecasting. Here, we propose DeepYield, a combined structure, that integrates the ConvLSTM layers with the 3-Dimensional CNN (3DCNN) for more accurate and reliable spatiotemporal feature extraction. The models are trained by using county-based historical yield data and MODIS Land Surface Temperature (LST), Surface Reflectance (SR), and Land Cover (LC) data over 1836 primary soybean growing counites in the Contiguous United States (CONUS). The forecasting performance of the developed models is compared against the competing approaches including Decision Trees, CNN + GP, and CNN-LSTM and results indicate that DeepYield significantly outperforms these techniques and also performs better than both ConvLSTM and 3DCNN.
This repository contains codes for the paper: Abbaszadeh, P., H. Moradkhani, K. Gavahai, S. Kumar, C. Hain, X. Zhan, Q. Duan, C. Peters-Lidard, and M. Karimiziarani (2021) High-Resolution SMAP Satellite Soil Moisture Product: Exploring the Opportunities, Bulletin of the American Meteorological Society, doi: 10.1175/BAMS-D-21-0016.1
Abstract: The amount (soil moisture) and state (freeze-thaw) of the water in soil plays a pivotal role in global water, energy, and carbon cycles. The water content of the top few centimeters (∼5 cm) of soil is typically referred to as surface soil moisture (SSM), which defines how wet or dry the soil is in its top layer. SSM is a key component of the microclimate that governs the interaction of water and heat fluxes between the ground and the atmosphere, regulating air temperature and humidity, and thus, affecting climatic conditions and weather changes. Knowledge of the temporal dynamics and spatial variability of soil moisture is crucial in understanding many environmental processes and their impacts on plant fertility, crop yields, droughts, or exposure to flood hazards.