Search

Accurate prediction of hydrological variables (HVs) is critical for understanding hydrological processes. Deep learning (DL) models have shown excellent forecasting abilities for different HVs. However, most DL models typically predicted HVs independently, without satisfying the principle of water balance. This missed the interactions between different HVs in the hydrological system and the underlying physical rules. In this study, we developed a DL model based on multitask learning and hybrid physically constrained schemes to simultaneously forecast soil moisture, evapotranspiration, and runoff. The models were trained using ERA5-Land data, which have water budget closure. We thoroughly assessed the advantages of the multitask framework and the proposed constrained schemes. Results showed that multitask models with different loss-weighted strategies produced comparable or better performance compared to the single-task model. The multitask model with a scaling factor of 5 achieved the best among all multitask models and performed better than the single-task model over 70.5% of grids. In addition, the hybrid constrained scheme took advantage of both soft and hard constrained models, providing physically consistent predictions with better model performance. The hybrid constrained models performed the best among different constrained models in terms of both general and extreme performance. Moreover, the hybrid model was affected the least as the training data were artificially reduced, and provided better spatiotemporal extrapolation ability under different artificial prediction challenges. These findings suggest that the hybrid model provides better performance compared to previously reported constrained models when facing limited training data and extrapolation challenges. [ABSTRACT FROM AUTHOR]

Soil moisture (SM) is a key variable in Earth system science that affects various hydrological and agricultural processes. Convolutional long short-term memory (Conv-LSTM) networks are widely used deep learning models for spatio-temporal SM prediction, but they are often regarded as black boxes that lack interpretability and transparency. This study aims to interpret Conv-LSTM for spatio-temporal SM prediction in China, using the permutation importance and smooth gradient methods for global and local interpretation, respectively. The trained Conv-LSTM model achieved a high R2 of 0.92. The global interpretation revealed that precipitation and soil properties are the most important factors affecting SM prediction. Furthermore, the local interpretation showed that the seasonality of variables was more evident in the high-latitude regions, but their effects were stronger in low-latitude regions. Overall, this study provides a novel approach to enhance the trust-building for Conv-LSTM models and to demonstrate the potential of artificial intelligence-assisted Earth system modeling and understanding element prediction in the future. [ABSTRACT FROM AUTHOR]

Global carbon fluxes describe the carbon exchange between land and atmosphere. However, already available global carbon fluxes datasets have not been adjusted by the available site data and deep learning tools. In this work, a global carbon fluxes dataset (named as GCFD) of gross primary productivity (GPP), terrestrial ecosystem respiration (RECO), and net ecosystem exchange (NEE) has been developed via a deep learning based convolutional neural network (CNN) model. The dataset has a spatial resolution of 1 km at three time steps per month from January 1999 to June 2020. Flux measurements were used as a training target while remote sensing of vegetation conditions and meteorological data were used as predictors. The results showed that CNN could outperform other commonly used machine learning methods such as random forest (RF) and artificial neural network (ANN) by leading to satisfactory performance with R2 values of the validation stage as 0.82, 0.72 and 0.62 for GPP, RECO, and NEE modelling, respectively. Thus, CNN trained using reanalysis meteorological data and remote sensing data was chosen to produce the global dataset. GCFD showed higher accuracy and more spatial details than some other global carbon flux datasets with reasonable spatial pattern and temporal variation. GCFD is also in accordance with vegetation conditions detected by remote sensing. Owing to the obtained results, GCFD can be a useful reference for various meteorological and ecological analyses and modelling, especially when high resolution carbon flux maps are required. [ABSTRACT FROM AUTHOR]

Soil moisture (SM) has significant impacts on the Earth's energy and water cycle system. Remote sensing, such as the Soil Moisture Active Passive (SMAP) mission, has delivered valuable estimations of global surface soil moisture. However, it has a 2~3 days revisit time leading to gaps between SMAP areas. To achieve accurate and comprehensive real-time forecast of SM, we propose a spatial–temporal deep learning model based on the Convolutional Gated Recursive Units with Data Integration (DI_ConvGRU) to capture the spatial and temporal variation in SM simultaneously by modeling the influence of adjacent SM values in space and time. Experiments show that the DI_ConvGRU outperforms the ConvGRU with Linear Interpolation (interp_ConvGRU) and the Long Short-Term Memory with Data Integration (DI_LSTM). The best performance (Bias = 0.0132 m3/m3, ubRMSE = 0.022 m3/m3, R = 0.977) has been achieved through the use of spatial–temporal deep learning model and Data Integration term. In comparison with interp_ConvGRU and DI_LSTM, DI_ConvGRU has improved the model performance in 74.88% and 68.99% of the regions according to RMSE, respectively. The predictability of SM depends highly on SM memory characteristics. DI_ConvGRU can provide accurate spatial–temporal forecast for SM with missing data, making them potentially useful for applications such as filling observational gaps in satellite data. [ABSTRACT FROM AUTHOR]

The accurate prediction of surface soil moisture (SM) is crucial for understanding hydrological processes. Deep learning (DL) models such as the long short-term memory model (LSTM) provide a powerful method and have been widely used in SM prediction. However, few studies have notably high success rates due to lacking prior knowledge in forms such as causality. Here we present a new causality-structure-based LSTM model (CLSTM), which could learn time interdependency and causality information for hydrometeorological applications. We applied and compared LSTM and CLSTM methods for forecasting SM across 64 FLUXNET sites globally. The results showed that CLSTM dramatically increased the predictive performance compared with LSTM. The Nash–Sutcliffe efficiency (NSE) suggested that more than 67% of sites witnessed an improvement of SM simulation larger than 10%. It is highlighted that CLSTM had a much better generalization ability that can adapt to extreme soil conditions, such as SM response to drought and precipitation events. By incorporating causal relations, CLSTM increased predictive ability across different lead times compared to LSTM. We also highlighted the critical role of physical information in the form of causality structure to improve drought prediction. At the same time, CLSTM has the potential to improve predictions of other hydrometeorological variables. [ABSTRACT FROM AUTHOR]

Accurate spatiotemporal predictions of surface soil moisture (SM) are important for many critical applications. Machine learning models provide a powerful method for building an accurate and reliable predictive model of SM. However, the models used in recent studies have some limitations, including lack of spatial autocorrelation (SAC), vague representation of important features, and primarily focused on the one-step forecast. Thus, we proposed an attention-based convolutional long short-term memory model (AttConvLSTM) for multistep forecasting. The model includes three layers, spatial compression, axial attention, and encoder–decoder prediction, which are used for compressing spatial information, feature extraction, and multistep prediction, respectively. The model was trained using surface SM from the Soil Moisture Active Passive L4 product at 18-km spatial resolution over the United States. The results show that AttConvLSTM predicts 24 h ahead SM with mean R2 and RMSE is equal to 0.82 and 0.02, respectively. Compared with LSTM, AttConvLSTM improves the model performance over 73.6% of regions, with an improvement of 8.4% and 17.4% in R2 and RMSE, respectively. The performance of the model is mainly influenced by temporal autocorrelation (TAC). Moreover, we also highlight the importance of SAC on model performance, especially over regions with high SAC and low TAC. Our model is also competent for SM predictions from several hours to several days, which could be a useful tool for predicting all meteorological variables and forecasting extremes. [ABSTRACT FROM AUTHOR]

The advancements in deep learning methods have presented new opportunities and challenges for predicting land surface variables (LSVs) due to their similarity with computer sciences tasks. However, few researchers focus on the benchmark datasets for LSVs predictions that hampers fair comparisons of different data-driven deep learning models. Hence, we propose a LSVs benchmark dataset and prediction toolbox to boost research in data-driven LSVs modeling and improve the consistency of data-driven deep learning models for LSVs. LSVs benchmark dataset contains a large number of hydrology-related variables, such as global soil moisture, runoff, etc., which can verify the simulation of hydrological processes. Various global data from European Centre for Medium-Range Weather Forecasts reanalysis 5 (ERA5), ERA5-land, global gridded soil information (SoilGrid), soil moisture storage capacity (SMSC), and moderate-resolution imaging spectroradiometer (MODIS) datasets have been pre-processed into daily data at 0.5-, 1-, 2-, and 4-degree resolutions to facilitate their use in data-driven models. Simple statistical metrics, i.e., the root mean squared error and correlation coefficient, are chosen to evaluate the performance of different deep learning (DL) models, including convolutional neural network, long short-term memory and convolution long short-term memory models, with lead times of 1 and 5 days. A processed-based model serves as a physic baseline, soil moisture and surface sensible heat fluxes are taken as the target variables. The developed benchmark dataset and evaluation metrics for predicting LSVs using data-driven approaches, named as the LandBench toolbox, were implemented using Pytorch. This toolbox facilitates the reimplementation of existing methods, the development of novel predictive models, and the utilization of unified evaluation metrics. Additionally, the toolbox incorporates address mapping technology to enable high-resolution global predictions with constrained computing resources. We hope LandBench will not only serves as a standardized framework, fostering equitable model comparisons, but also provides indispensable data and a robust scientific foundation essential for advancing climate change research, disaster management, and sustainable development initiatives. [ABSTRACT FROM AUTHOR]

• Interdependencies enhance performance in covariate analysis. • The proposed model outperforms existing methods. • The proposed model expands DSM application possibilities. The accurate and cost-effective mapping of soil texture is essential for agricultural development and environmental activities. Soil texture exhibits high spatial heterogeneity which poses challenges for recent Digital Soil Mapping (DSM) methods in achieving accurate predictions. Feature engineering methods, extensively used to capture complex soil-forming relationships and enhance prediction accuracy, often involve labor-intensive processes. Additionally, the engineered "discrete" feature cannot reflect interactions between environmental covariates or dependencies. To address the challenges, this study proposes a novel Local-Global Dependency Long Short-Term Memory model (LGD-LSTM) to enhance soil texture predictions at various soil depths. Firstly, a covariate reorganization method has been devised to generate multiple sets of input. Subsequently, several Long Short-Term Memory models (LSTM) have been employed to extract the interdependencies among the covariates. Finally, predictions are generated using a fully-connected layer. Cross-validation was conducted within this experiment to analyze prediction accuracy: the average explained variation (R2) ranged from 0.66 to 0.73, and the root mean square error (RMSE) ranged from 6.52% to 10.89%. The results indicated that the LGD-LSTM model offers distinct advantages over other digital soil mapping methods, including Random Forests (RF), Convolutional Neural Network (CNN), and the standard Long Short-Term Memory model (LSTM). In summary, this LGD-LSTM method demonstrates superior performance with relatively high accuracy, ensuring its applicability in effectively representing spatial variations in soil texture. Furthermore, it presents a novel option for DSM applications, enhancing the field's methodology and potential impact. [ABSTRACT FROM AUTHOR]

• Incorporating meta -learning into LSTM model reduces the overall PBIAS by 8.68%, improving the overall KGE by 7% compared to standard LSTM model. • Meta-LSTM model improves extreme runoff prediction, enhancing FLV by 2.73% and FHV by 11.04%, aiding in better flood management strategies. • The proposed meta -learning framework enhances performance across various deep learning models, demonstrating its versatility in runoff prediction tasks. In the field of hydrology, deep learning has become a prevalent tool for runoff simulation. However, the limitations stem from their primary focus on normality, which fails to accurately capture rare events. This study introduces a novel Long Short-Term Memory (LSTM) model, termed Meta-LSTM, which is based on the Model-Agnostic Meta-Learning (MAML) framework. The Meta-LSTM model is capable of dynamically fine-tuning its parameters to ensure effective adaptation to various runoff scenarios. From this Meta-LSTM model, the Meta-enhanced paradigm is subsequently proposed, ensuring effective adaptation to diverse models and datasets. We conducted experiments with various models on the CAMELS and CAMELS-AUS datasets. Compared to conventional deep learning models for runoff simulation, Meta-enhanced models exhibit substantial improvements. Specifically, the Meta-LSTM model reduces the PBIAS from −13.86 % to −5.18 %, increasing the Kling-Gupta Efficiency (KGE) by 7 % on the CAMELS dataset. For the Meta-GR4J-CNN model, the PBIAS decreases by 21 %, and the Nash-Sutcliffe Efficiency (NSE) increases by 2 % on the CAMELS-AUS dataset. This demonstrates the ability of the Meta-enhanced model to more accurately represent observed data without significant additional time costs. Our approach overcomes the problem of uniform training in simulations of complex scenarios and promises to significantly improve the accuracy of future hydrologic studies. [ABSTRACT FROM AUTHOR]

An accurate vehicle trajectory prediction promotes understanding of the traffic environment and enables task criticality assessment in advanced driver assistance systems (ADASs) in autonomous vehicles and intelligent connected vehicles. Nevertheless, conventional prediction models are characterized by low prediction accuracy, the inability of long-term prediction, and a single-road section adaptation. To tackle these limitations, this study proposes a trajectory prediction model based on a deep encoder–decoder and a deep neural network (DNN). One modification included introducing an attention mechanism into the traditional encoder–decoder framework. Overall, 1794,1400,2100 trajectory samples from highways, intersections, and roundabouts are used to train the proposed framework and obtain optimal deep encoder–decoder architectures for different road section types. Since the experiments revealed no significant advantages of using the attention mechanism in deep encoder–decoder, the mechanism is not included in the optimal architecture. Next, to achieve higher prediction accuracy and better long-term prediction capability, different DNN structures are tested as trajectory correction networks, and the optimal DNN structure is selected. Finally, the experiments are conducted using the proposed deep encoder–decoder framework and the optimal DNN. The results show that the proposed model reaches 92.87%, 86.65%, and 89.15% average trajectory fit ratio (TFR) on a highway, intersection, and a roundabout, respectively. Therefore, the model enables accurate long-term predictions of vehicle trajectories in these road segments. The proposed model and presented results provide a basis for ADASs' trajectory prediction algorithms. [ABSTRACT FROM AUTHOR]

• Skillful prediction of soil moisture (SM) is useful but great challenges exist. • A novel encoder-decoder LSTM model with residual learning (EDR-LSTM) is developed. • EDR-LSTM improved about 20% in SM prediction at the lead time of 3, 5 and 10 days. • Both encoder-decoder and residual learning are useful in improving SM prediction. • The predictability of SM over various conditions was widely investigated. The skillful prediction of soil moisture can provide much help for many practical applications including ecosystem management and precision agriculture. It presents great challenges because the future variation of soil moisture has much uncertainty. Therefore, a novel encoder-decoder deep learning model with residual learning based on Long Short-Term Memory (EDT-LSTM) is developed in this study as an alternative data-intelligence tool. This model includes two layers: the encoder-decoder LSTM layer and LSTM with a fully connected layer, which is used to enhance the prediction ability by considering the intermediate time-series data between the input time step and the predictive time step. We tested EDT-LSTM for soil moisture prediction at the lead time of 1, 3, 5, 7 and 10 days by using data from FLUXNET sites. The result shows that the improvements brought by EDT-LSTM were about 7.95% (1 day), 10.10% (3 days), 12.68% (5 days), 15.49% (7 days) and 19.71% (10 days) in average according to the R2 taking LSTM as the baseline. Furthermore, the predictability of soil moisture over various conditions (i.e., different hyper-parameters in EDT-LSTM, different predictive models, different climate regions and different sites) has been widely discussed for the understanding of models' behavior in this paper. The proposed EDT-LSTM offered a new tool to predict soil moisture better. The code of EDT-LSTM is publicly available at https://github.com/ljz1228/CLM-LSTM-soil-moisture-prediction. [ABSTRACT FROM AUTHOR]

• A novel attention-aware LSTM model (ILSTM_Soil) is developed for soil prediction. • The temporal and predictor's importances are widely investigated. • The interpretation of attention weights coincides well with physical knowledge. • ILSTM_Soil model outperforms other existing predictive models in most cases. • Attention mechanism is advocated for better performance and interoperability. Accurate prediction of soil moisture (SM) and soil temperature (ST) plays an important role in Earth system science, helping to forecast and understand ecosystem changes. They present great challenges because land-atmospheric interactions are complex and diverse in space and time. Although deep learning methods have excellent performance for land surface variables' prediction such as SM and ST, they are often questioned due to their over-parameterized black-box nature and neglect of physical knowledge and interpretability. From this, we propose an attention-aware LSTM Model (ILSTM_Soil) by taking multi-feature attention, predictor attention and temporal attention into account. We first used LSTM to generate multi-feature vectors of all predictors, and then the three attention mechanisms were designed to summarize these feature vectors for SM and ST prediction. Experiment results for SM and ST prediction at the lead time of 1 and 7 days on ten FLUXNET sites suggest that the proposed ILSTM_Soil model outperforms Random Forest (RF), Support Vector Regression (SVR), Elastic-Net (ENET), original Long Short-Term Memory (LSTM), and attention LSTM (A-LSTM) models in most cases. The interpretation of attention weights verifies that the proposed model can capture physical knowledge over SM and ST. The code of ILSTM_Soil is made publicly available and we hope it can encourage researchers to develop effective DL models in land surface variables' prediction conveniently. [ABSTRACT FROM AUTHOR]

• Deep learning models predicted soil moisture well with limited SMAP samples. • Transfer learning improved predictions with additional samples from ERA5-land. • Transfer ConvLSTM performed the best with over 90% variation explained. • The predictive ability of different factors was widely investigated. • Transfer learning is advocated for datasets with limited samples like SMAP. The skillful soil moisture (SM) for the Soil Moisture Active Passive (SMAP) L4 product can provide substantial value for many practical applications including ecosystem management and precision agriculture. Deep learning (DL) models provide powerful methods for hydrologic variables' prediction such as SM. However, the sample size of daily SM in the SMAP product is quite small, which may lead to overfitting and further impact the accuracy of DL models. From this, we first tested whether excellent predictive performance can be achieved with limited SMAP samples by the Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Convolutional LSTM (ConvLSTM) models, which are frequent used for hydrologic prediction. Then we pre-trained the DL models in the source domain (ERA5-land) and fine-tuned them in the target domain (SMAP). The results show that the transfer ConvLSTM model had the highest R2 ranging from 0.909 to 0.916 and the lowest RMSE ranging from 0.0239 to 0.0247 for the lead time of 3, 5 and 7 days, and the regression lines between the predicted and the observed SM were closer to the ideal line (y = x) than all the other DL models. All the performances of transfer DL models were better than those of their corresponding DL models without transfer learning and some regions witnessed an increased explained variation over 20%. The predictive ability of different factors (i.e., lagged SM, soil temperature, season, and precipitation) has been widely discussed in this paper. According the results, we advocate for applying cross-source transfer learning with DL models for SM prediction in newly built datasets. [ABSTRACT FROM AUTHOR]

• A hybrid deep learning model is proposed. • The hybrid model performs very well in hourly streamflow prediction. • Significance of model inputs are investigated by quantifying their contributions to predictions. Process-based streamflow prediction is subjected to large uncertainties in model parameters and parameterizations related to the complex processes involved in streamflow generation. The data-driven models offer efficient alternatives without considering the physical processes, but their applications are limited by non-stationarity existing in observations. In this study, we propose a hybrid model, namely the DIFF-FFNN-LSTM model, to predict hourly streamflow. The model comprises three components, namely the first-order difference (DIFF), feedforward neural network (FFNN), and long short-term memory network (LSTM). When applied to the Andun basin of China, the proposed DIFF-FFNN-LSTM model performs very well in hourly streamflow prediction, with a RMSE of 9.31 m3/s with average streamflow rate of 54 m3/s and a MAE of 3.63 m3/s for all the flood events in the testing period. The comparison with five other machine learning models (of similar complexity or model structure) and four statistical models show superiority of our proposed DIFF-FFNN-LSTM model. The Shapley Additive exPlanations was used to quantify the contribution of each model input to the prediction skill. Streamflow at the previous hour was identified as the most important input, and streamflow generally contribute more than precipitation. Inputs closer to the prediction time do not necessarily have a greater impact on the model prediction. The study highlights the power of the combining of different data-driven methods and the promising prospect of our hybrid model in hydrological predictions. [ABSTRACT FROM AUTHOR]