A Review of Machine Learning Applications in Land Surface Modeling

Abstract

Machine learning (ML), as an artificial intelligence tool, has acquired significant progress in data-driven research in Earth sciences. Land Surface Models (LSMs) are important components of the climate models, which help to capture the water, energy, and momentum exchange between the land surface and the atmosphere, providing lower boundary conditions to the atmospheric models. The objectives of this review paper are to highlight the areas of improvement in land modeling using ML and discuss the crucial ML techniques in detail. Literature searches were conducted using the relevant key words to obtain an extensive list of articles. The bibliographic lists of these articles were also considered. To date, ML-based techniques have been able to upgrade the performance of LSMs and reduce uncertainties by improving evapotranspiration and heat fluxes estimation, parameter optimization, better crop yield prediction, and model benchmarking. Widely used ML techniques used for these purposes include Artificial Neural Networks and Random Forests. We conclude that further improvements in land modeling are possible in terms of high-resolution data preparation, parameter calibration, uncertainty reduction, efficient model performance, and data assimilation using ML. In addition to the traditional techniques, convolutional neural networks, long short-term memory, and other deep learning methods can be implemented.

Artificial Intelligence for Earth System Predictability (AI4ESP) (2021 Workshop Report)

“…Furthermore, we need to begin to explore how to integrate AI into models and develop hybrid modeling approaches using transferable AI methods. These models have been developed for a variety of land processes including crop yields, evapotranspiration, soil moisture, momentum, and heat fluxes (Pal and Sharma 2021). However, scaling these ML models from site to global scales requires additional remote sensed data.…”

Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning

“…Outside the polar regions, where observations have historically been more readily available, machine learning (ML) has emerged in recent years as an alternative strategy for parametrizing boundary‐layer processes (Pal & Sharma, 2021). The basic idea of the ML or data‐driven approach is that, given sufficient observational data, statistical algorithms can be used to directly infer empirical relationships between quantities of interest, such as surface turbulent fluxes, and mean meteorological variables such as temperature, humidity, etc.…”

Estimation of the Surface Fluxes for Heat and Momentum in Unstable Conditions with Machine Learning and Similarity Approaches for the LAFE Data Set

“…Particularly, machine learning (ML) approaches hold great promise because of their capability to detect nonlinear relationships in large data sets without any constraints by the similarity relationships and self-correlations of variables prescribed in MOST and BRN. An overview of ML methods in L-A system research is given in Zhang (2008); Pal and Sharma (2019).…”