LandBench 1.0: A benchmark dataset and evaluation metrics for data-driven land surface variables prediction

Li, Qingliang; Zhang, Cheng; Shangguan, Wei; Wei, Zhongwang; Yuan, Hua; Zhu, Jinlong; Li, Xiaoning; Li, Lu; Li, Gan; Liu, Pingping; Dai, Yongjiu

doi:10.1016/j.eswa.2023.122917

Cited by 5 publications

(3 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our research extends the foundational work of Li et al [49] on LandBench, which has established a benchmark dataset and predictive toolkit specifically tailored to propel advancements in data-driven modeling of surface variables. LandBench is pivotal in enhancing the robustness of deep learning frameworks for surface variable predictions and in bridging interdisciplinary collaborations between computer science and earth system science communities.…”

Section: Model Setting Trainingmentioning

confidence: 74%

Enhancing Soil Moisture Forecasting Accuracy with REDF-LSTM: Integrating Residual En-Decoding and Feature Attention Mechanisms

Li,

Zhang,

et al. 2024

Water

Self Cite

View full text Add to dashboard Cite

This study introduces an innovative deep learning model, Residual-EnDecode-Feedforward Attention Mechanism-Long Short-Term Memory (REDF-LSTM), designed to overcome the high uncertainty challenges faced by traditional soil moisture prediction methods. The REDF-LSTM model, by integrating a residual learning encoder–decoder LSTM layer, enhanced LSTM layers, and feedforward attention, not only captures the deep features of time series data but also optimizes the model’s ability to identify key influencing factors, including land surface features, atmospheric conditions, and other static environmental variables. Unlike existing methods, the innovation of this model lies in its first-time combination of the residual learning encoder–decoder and feedforward attention mechanisms in the soil moisture prediction field. It delves into the complex patterns of time series through the encoder–decoder structure and accurately locates key influencing factors through the feedforward attention mechanism, significantly improving predictive performance. The choice to combine the feedforward attention mechanism and encoder–decoder with the LSTM model is to fully leverage their advantages in processing complex data sequences and enhancing the model’s focus on important features, aiming for more accurate soil moisture prediction. After comparison with current advanced models such as EDLSTM, FAMLSTM, and GANBiLSTM, our REDF-LSTM demonstrated the best performance. Compared to traditional LSTM models, it achieved an average improvement of 13.07% in R2, 20.98% in RMSE, 24.86% in BIAS, and 11.1% in KGE key performance indicators, fully proving its superior predictive capability and potential application value in precision agriculture and ecosystem management.

show abstract

Section: Model Setting Trainingmentioning

confidence: 74%

Enhancing Soil Moisture Forecasting Accuracy with REDF-LSTM: Integrating Residual En-Decoding and Feature Attention Mechanisms

Li,

Zhang,

et al. 2024

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…This dataset includes a wide range of global variables from the ERA5-Land, ERA5 reanalysis, SoilGrid, SMSC, and MODIS datasets. The data has been processed into daily records at resolutions of 0.5°, 1°, 2°, and 4° for application in data-driven models (Feng et al, 2020;Li et al, 2024). In this study, we utilize data with a resolution of 0.5°.…”

Section: Data Sourcesmentioning

confidence: 99%

“…In the parameter adjustment section, reference was made to our previous work (Li et al, 2024). The hyperparameters of the model were set as follows: 1000 epochs, but typically, the model reached its optimal performance after approximately 200-300 epochs.…”

Section: Model Training and Parameter Adjustmentmentioning

confidence: 99%

Enhancing data-driven soil moisture modeling with physically-guided LSTM networks

Geng,

Yan,

et al. 2024

Front. For. Glob. Change

Self Cite

View full text Add to dashboard Cite

In recent years, deep learning methods have shown significant potential in soil moisture modeling. However, a prominent limitation of deep learning approaches has been the absence of physical mechanisms. To address this challenge, this study introduces two novel loss functions designed around physical mechanisms to guide deep learning models in capturing physical information within the data. These two loss functions are crafted to leverage the monotonic relationships between surface water variables and shallow soil moisture as well as deep soil water. Based on these physically-guided loss functions, two physically-guided Long Short-Term Memory (LSTM) networks, denoted as PHY-LSTM and PHYs-LSTM, are proposed. These networks are trained on the global ERA5-Land dataset, and the results indicate a notable performance improvement over traditional LSTM models. When used for global soil moisture forecasting for the upcoming day, PHY-LSTM and PHYs-LSTM models exhibit closely comparable results. In comparison to conventional data-driven LSTM models, both models display a substantial enhancement in various evaluation metrics. Specifically, PHYs-LSTM exhibits improvements in several key performance indicators: an increase of 13.6% in Kling-Gupta Efficiency (KGE), a 20.7% increase in Coefficient of Determination (R2), an 8.2% reduction in Root Mean Square Error (RMSE), and a 4.4% increase in correlation coefficient (R). PHY-LSTM also demonstrates improvements, with a 14.8% increase in KGE, a 19.6% increase in R2, an 8.2% reduction in RMSE, and a 4.4% increase in R. Additionally, both models exhibit enhanced physical consistency over a wide geographical area. Experimental results strongly emphasize that the incorporation of physical mechanisms can significantly bolster the predictive capabilities of data-driven soil moisture models.

show abstract

Improving global soil moisture prediction through cluster-averaged sampling strategy

Li,

Xiao,

Zhang

et al. 2024

Geoderma

View full text Add to dashboard Cite

LandBench 1.0: A benchmark dataset and evaluation metrics for data-driven land surface variables prediction

Cited by 5 publications

References 70 publications

Enhancing Soil Moisture Forecasting Accuracy with REDF-LSTM: Integrating Residual En-Decoding and Feature Attention Mechanisms

Enhancing Soil Moisture Forecasting Accuracy with REDF-LSTM: Integrating Residual En-Decoding and Feature Attention Mechanisms

Enhancing data-driven soil moisture modeling with physically-guided LSTM networks

Improving global soil moisture prediction through cluster-averaged sampling strategy

Contact Info

Product

Resources

About