Use of multiple LIDAR-derived digital terrain indices and machine learning for high-resolution national-scale soil moisture mapping of the Swedish forest landscape

Ågren, Anneli; Larson, Johannes; Paul, Siddhartho Shekhar; Laudon, Hjalmar; Lidberg, William

doi:10.1016/j.geoderma.2021.115280

Cited by 66 publications

(35 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another big asset of the Finish maps is also the classification according to seasonal recommendations for the execution of operations [65]. Such a feature current DTW maps are generally lacking, since they just define an area as "wet" or "dry" [45 •], although attempts to further classifications into various wetness categories are in progress [66]. Therefore, it would be a worthwhile endeavour to governmentally provide comprehensive trafficability maps, covering European forests.…”

Section: Discussionmentioning

confidence: 99%

“…Metsaan.fi is a service for forest owner to easily access the information of their own forest and to use digital forest services. The trafficability maps are today widely used in Finnish forestry by forest operation managers and forest machine operators [66].…”

Section: Finlandmentioning

confidence: 99%

“…DTW maps were prepared by the Swedish forest agency over the whole country since 2014 and were freely available through their online map services. The maps had been used by majority of forestry companies since about 5 years and contributed to improve planning of different forest operations [66].…”

Section: Swedenmentioning

confidence: 99%

See 2 more Smart Citations

Trafficability Prediction Using Depth-to-Water Maps: the Status of Application in Northern and Central European Forestry

et al. 2022

View full text Add to dashboard Cite

Purpose of Review Mechanized logging operations with ground-based equipment commonly represent European production forestry but are well-known to potentially cause soil impacts through various forms of soil disturbances, especially on wet soils with low bearing capacity. In times of changing climate, with shorter periods of frozen soils, heavy rain fall events in spring and autumn and frequent needs for salvage logging, forestry stakeholders face increasingly unfavourable conditions to conduct low-impact operations. Thus, more than ever, planning tools such as trafficability maps are required to ensure efficient forest operations at reduced environmental impact. This paper aims to describe the status quo of existence and implementation of such tools applied in forest operations across Europe. In addition, focus is given to the availability and accessibility of data relevant for such predictions. Recent Findings A commonly identified method to support the planning and execution of machine-based operations is given by the prediction of areas with low bearing capacity due to wet soil conditions. Both the topographic wetness index (TWI) and the depth-to-water algorithm (DTW) are used to identify wet areas and to produce trafficability maps, based on spatial information. Summary The required input data is commonly available among governmental institutions and in some countries already further processed to have topography-derived trafficability maps and respective enabling technologies at hand. Particularly the Nordic countries are ahead within this process and currently pave the way to further transfer static trafficability maps into dynamic ones, including additional site-specific information received from detailed forest inventories. Yet, it is hoped that a broader adoption of these information by forest managers throughout Europe will take place to enhance sustainable forest operations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Finlandmentioning

confidence: 99%

See 1 more Smart Citation

Trafficability Prediction Using Depth-to-Water Maps: the Status of Application in Northern and Central European Forestry

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Compared with RF and other some methods, XGB has significantly faster calculation speed (Fan et al, 2018;Shi et al, 2021). Some studies have shown that XGB is a better regression and classification algorithm than RF and other machine learning methods (Ågren et al, 2021;Fan et al, 2021).…”

Section: Machine Learning Methodsmentioning

confidence: 99%

“…Although these machine learning methods perform well in constructing nonlinear regression models, there are still some shortcomings. For example, neural networks are prone to overfitting when there are inefficient samples (Piotrowski and Napiorkowski, 2013) or variables that are weakly correlated with the dependent variable (Elshorbagy and Parasuraman, 2008;Ågren et al, 2021). Extreme gradient boosting (XGB), as a new ensemble learning method (Chen and Guestrin, 2016), performs well in some fields (Wang et al, 2020;Fan et al, 2021;Ma et al, 2021), but it has rarely been used for soil moisture downscaling.…”

Section: Introductionmentioning

confidence: 99%

Daily soil moisture mapping at 1 km resolution based on SMAP data for areas affected by desertification in Northern China

Rao

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

Abstract. Land surface soil moisture (SM) plays a critical role in hydrological processes and terrestrial ecosystems in areas affected by desertification. Passive microwave remote sensing products such as the Soil Moisture Active Passive (SMAP) have been shown to monitor surface soil water well. However, the coarse spatial resolution and lack of full coverage of these products greatly limit their application in areas undergoing desertification. In order to overcome these limitations, a combination of multiple machine learning methods, including multiple linear regression (MLR), support vector regression (SVR), artificial neural networks (ANN), random forest (RF) and extreme gradient boosting (XGB), have been applied to downscale the 36 km SMAP SM products and produce higher spatial-resolution SM data based on related surface variables, such as vegetation index and surface temperature. Areas affected by desertification in Northern China, which are very sensitive to SM, were selected as the study area, and the downscaled SM with a resolution of 1 km on a daily scale from 2015 to 2020 was produced. The results show a good performance compared with in situ observed SM data, with an average unbiased root mean square error value of 0.049 m3/m3. In addition, their time series are also consistent with precipitation and perform better than some common gridded SM products. The data can be used to assess soil drought and provide a reference for reversing desertification in the study area. This dataset is freely available at https://doi.org/10.6084/M9.FIGSHARE.16430478.V5 (Rao et al., 2021).

show abstract

Riparian buffer zones in production forests create unequal costs among forest owners

Bakx,

Akselsson,

Droste

et al. 2024

Eur J Forest Res

View full text Add to dashboard Cite

Riparian buffer zones (RBZs) are an important instrument for environmental policies for water and biodiversity protection in managed forests. We investigate the variation of the cost of implementing RBZs within different property size classes across the size range of non-industrial forest owner properties in Southern Sweden. Using the Heureka PlanWise decision support system, we quantified the cost of setting aside RBZs or applying alternative management in them, as the relative loss of harvest volume and of net present value per property. We did this for multiple simulated as well as real-world property distributions. The variation of cost distribution among small properties was 4.2–6.9 times higher than among large properties. The interproperty cost inequality decreased non-linearly with increasing property size and levelled off from around 200 ha. We conclude that RBZs, due to the irregular distribution of streams, cause highly unequal financial consequences for owners, with some small property owners bearing a disproportionally high cost. This adds to previous studies showing how environmental considerations differentially affect property owners. We recommend decision makers to stimulate the uptake of RBZs by alleviating these inequalities between forest owners by including appropriate cost sharing or compensation mechanisms in their design.

show abstract

Use of multiple LIDAR-derived digital terrain indices and machine learning for high-resolution national-scale soil moisture mapping of the Swedish forest landscape

Cited by 66 publications

References 63 publications

Trafficability Prediction Using Depth-to-Water Maps: the Status of Application in Northern and Central European Forestry

Trafficability Prediction Using Depth-to-Water Maps: the Status of Application in Northern and Central European Forestry

Daily soil moisture mapping at 1 km resolution based on SMAP data for areas affected by desertification in Northern China

Riparian buffer zones in production forests create unequal costs among forest owners

Contact Info

Product

Resources

About