Abstract
Spatially extensive high-resolution soil moisture mapping is valuable in practical forestry and land management, but challenging. Here we present a novel technique involving use of LIDAR-derived terrain indices and machine learning (ML) algorithms capable of accurately modeling soil moisture at 2 m spatial resolution across the entire Swedish forest landscape. We used field data from about 20,000 sites across Sweden to train and evaluate multiple ML models. The predictor features (variables) included a suite of terrain indices generated from a national LIDAR digital elevation model and ancillary environmental features, including surficial geology, climate and land use, enabling adjustment of soil moisture class maps to regional or local conditions. Extreme gradient boosting (XGBoost) provided better performance for a 2-class model, manifested by Cohen’s Kappa and Matthews Correlation Coefficient (MCC) values of 0.69 and 0.68, respectively, than the other tested ML methods: Artificial Neural Network, Random Forest, Support Vector Machine, and Naïve Bayes classification. The depth to water index, topographic wetness index, and ‘wetland’ categorization derived from Swedish property maps were the most important predictors for all models. The presented technique enabled generation of a 3-class model with Cohen’s Kappa and MCC values of 0.58. In addition to the classified moisture maps, we investigated the technique’s potential for producing continuous soil moisture maps. We argue that the probability of a pixel being classified as wet from a 2-class model can be used as a 0–100% index (dry to wet) of soil moisture, and the resulting maps could provide more valuable information for practical forest management than classified maps.
Highlights
Soil moisture plays crucial roles in terrestrial ecosystem processes, including energy, water, and carbon cycles (Seneviratne et al, 2010)
The results demonstrated the potential utility of the approach, but so far efforts to map soil moisture using digital terrain indices have mostly focused on locating soils at the wet end of the spectrum, as wet soils are most sensitive to rut formation during forestry operations (Lidberg et al, 2020; White et al, 2012; Ågren et al, 2014b)
The performance of the machine learning (ML) algorithms was similar in terms of Kappa and Mat thews Correlation Coefficient (MCC) statistics obtained from comparison of predicted and regis tered soil moisture classes for the NFI plots in the test set
Summary
Soil moisture plays crucial roles in terrestrial ecosystem processes, including energy, water, and carbon cycles (Seneviratne et al, 2010). Spatially explicit assessment of soil moisture is essential for un derstanding energy and water budgets at scales ranging from local to global (Ali et al, 2015). Remote sensors of various kinds (e.g., passive, active or thermal) are mainly used for spatially extensive soil moisture mapping (Mohanty et al, 2017; Zeng et al, 2019). Soil moisture maps derived from previous generations of satellite remote sensing systems generally have much too low spatial resolution for practical purposes (Mohanty et al, 2017), even with the use of algorithms that can enhance resolution to 500–1000 m (Bauer-Marschallingere et al, 2019; Sabaghy et al, 2020; Zeng et al, 2019). There are clear needs for alternative methods that can provide accurate soil moisture maps with high spatial resolution
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
