Advances in soil moisture retrieval from multispectral remote sensing using unoccupied aircraft systems and machine learning techniques

Abstract

Abstract. This study investigates the ability of machine learning models to retrieve the surface soil moisture of a grassland area from multispectral remote sensing carried out using an unoccupied aircraft system (UAS). In addition to multispectral images, we use terrain attributes derived from a digital elevation model and hydrological variables of precipitation and potential evapotranspiration as covariates to predict surface soil moisture. We tested four different machine learning algorithms and interrogated the models to rank the importance of different variables and to understand their relationship with surface soil moisture. All the machine learning algorithms we tested were able to predict soil moisture with good accuracy. The boosted regression tree algorithm was marginally the best, with a mean absolute error of 3.8 % volumetric moisture content. Variable importance analysis revealed that the four most important variables were precipitation, reflectance in the red wavelengths, potential evapotranspiration, and topographic position indices (TPI). Our results demonstrate that the dynamics of soil water status across heterogeneous terrain may be adequately described and predicted by UAS remote sensing and machine learning. Our modeling approach and the variable importance and relationships we have assessed in this study should be useful for management and environmental modeling tasks where spatially explicit soil moisture information is important.

Improved understanding of vegetation dynamics and wetland ecohydrology via monthly UAV‐based classification

“…Such improved understanding of water‐vegetation relationships can assist the prediction of soil moisture using statistical or machine learning models, as previous applications based on fine resolution imagery often met challenges due to the lack of fine‐resolution input features that were able to interpret the extreme spatial heterogeneity in soil moisture (e.g., Araya et al, 2021; Zaman et al, 2012). Given the bidirectional relationships observed in our wetland, vegetation classification and the following species‐level analysis of VIs can potentially help the direct prediction of soil moisture distribution, which is a planned next step in research at the study site.…”

A Decade of Data‐Driven Water Budgets: Synthesis and Bibliometric Review

“…Deep learning is being applied to satellite and in situ data to produce daily soil moisture measurements at 9 km spatial resolution (Liu et al., 2022). Recent advances in unmanned aerial vehicles may also improve the scalability of DDWB methods (Kalua et al., 2020) such as soil moisture mapping by unpiloted aerial systems (Araya et al., 2021). Future research into how these new data sets can be incorporated into a DDWB, along with artificial intelligence and machine learning, are at the current frontier of tools for improving water management at all scales.…”

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

“…There are numerous opportunities to use ML to improve data collection by either direct or proxy measurements. These include approaches to collect new measurements of variables of interest (e.g., nutrients) across heterogeneous landscapes at much greater scales and resolutions through the use of automated ML-assisted technologies such as next-generation sensor networks, camera and video imagery processed using mature computer vision methods, autonomous UAV (Song et al 2017;Araya et al 2021), mobile aquatic drones (Matos and Postolache 2016), and robotics (e.g., Figure 3-2). Classification methods that combine different data layers can be used to determine optimal measurement strategies and sampling network design .…”