Mapping LUCAS topsoil chemical properties at European scale using Gaussian process regression

Ballabio, Cristiano; Lugato, Emanuele; Fernández‐Ugalde, Oihane; Orgiazzi, Alberto; Jones, Arwyn; Borrelli, Pasquale; Montanarella, Luca; Panagos, Panos

doi:10.1016/j.geoderma.2019.113912

Cited by 202 publications

(126 citation statements)

References 53 publications

(61 reference statements)

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…The observed over or underestimation of pH values is relatively low compared to other soil pH mapping studies using satellite data [10]. The relative lower error may be a result of the higher spatial resolution of Sentinel input data compared to the Landsat information used in previous studies [10], but may also result from the focus on soils under intensive agricultural management in our dataset and the use of soil only information in the prediction algorithm. An independent validation analysis was conducted on the second sampling campaign for pH detection on the "Stadtfeld" field, including a total number of 76 samples.…”

Section: Soil Property Predictionmentioning

confidence: 68%

“…Today, remote sensing data from satellites allow gathering spectral and temporal information. Such data help to interpret not only crop vitality (chlorophyll content) [6,7] and productivity (biomass) [8] but also soil properties, including physical (texture) [9], chemical (pH value or nutrient contents) [10], and biological (soil organic carbon) [11] properties.…”

Section: Introductionmentioning

confidence: 99%

“…Current soil property mapping campaigns have gained relatively high accuracy for the detection of chemical, physical, and biological soil properties such as pH [10], SOM [11] and clay content [9], respectively. Although these maps are relatively low in spatial and temporal resolution, they are needed for precision crop management.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Understanding Fields by Remote Sensing: Soil Zoning and Property Mapping

Yüzügüllü

Lorenz²,

Fröhlich³

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Precision agriculture aims to optimize field management to increase agronomic yield, reduce environmental impact, and potentially foster soil carbon sequestration. In 2015, the Copernicus mission, with Sentinel-1 and -2, opened a new era by providing freely available high spatial and temporal resolution satellite data. Since then, many studies have been conducted to understand, monitor and improve agricultural systems. This paper presents results from the SolumScire project, focusing on the prediction of the spatial distribution of soil zones and topsoil properties, such as pH, soil organic matter (SOM) and clay content in agricultural fields through random forest algorithms. For this purpose, samples from 120 fields were investigated. The zoning and soil property prediction has an accuracy greater than 90%. This is supported by a high agreement of the derived zones with farmer’s observations. The trained models revealed a prediction accuracy of 94%, 89% and 96% for pH, SOM and clay content, respectively. The obtained models for soil properties can support precision field management, the improvement of soil sampling and fertilization strategies, and eventually the management of soil properties such as SOM.

show abstract

Section: Soil Property Predictionmentioning

confidence: 68%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Understanding Fields by Remote Sensing: Soil Zoning and Property Mapping

Yüzügüllü

Lorenz²,

Fröhlich³

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Therefore, efforts to produce appropriate predictors to explain the spatial distribution of soil attributes (at detail and generalization) increases the accuracy of the models. Various covariates (e.g., climate, terrain attributes and RS data) representing soil state factors have been widely used in statistical models to predict soil texture, bulk density, organic carbon, nutrients (Ca, Mg, K, Na, N, P), available water capacity, pH and CEC [4,17,22,[34][35][36][37].…”

Section: Preparing Soil Covariatesmentioning

confidence: 99%

Mapping at 30 m Resolution of Soil Attributes at Multiple Depths in Midwest Brazil

et al. 2019

View full text Add to dashboard Cite

The Midwest region in Brazil has the largest and most recent agricultural frontier in the country where there is no currently detailed soil information to support the agricultural intensification. Producing large-extent digital soil maps demands a huge volume of data and high computing capacity. This paper proposed mapping surface and subsurface key soil attributes with 30 m-resolution in a large area of Midwest Brazil. These soil maps at multiple depth increments will provide adequate information to guide land use throughout the region. The study area comprises about 851,000 km2 in the Cerrado biome (savannah) in the Brazilian Midwest. We used soil data from 7908 sites of the Brazilian Soil Spectral Library and 231 of the Free Brazilian Repository for Open Soil Data. We selected nine key soil attributes for mapping and aggregated them into three depth intervals: 0–20, 20–60 and 60–100 cm. A total of 33 soil predictors were prepared using Google Earth Engine (GEE), such as climate and geologic features with 1 km-resolution, terrain and two new covariates with 30 m-resolution, based on satellite measurements of the topsoil reflectance and the seasonal variability in vegetation spectra. The scorpan model was adopted for mapping of soil variables using random forest regression (RF). We used the model-based optimization by tuning RF hyperparameters and calculated the scaled permutation importance of covariates in R software. Our results were promising, with a satisfactory model performance for physical and chemical attributes at all depth intervals. Elevation, climate and topsoil reflectance were the most important covariates in predicting sand, clay and silt. In general, for predicting soil chemical attributes, climatic variables, elevation and vegetation reflectance provided to be the most important of predictive components, while for organic matter it was a combination of climatic dynamics and reflectance bands from vegetation and topsoil. The multiple depth maps showed that soil attributes largely varied across the study area, from clayey to sandy, suggesting that less than 44% of the studied soils had good natural fertility. We concluded that key soil attributes from multiple depth increments can be mapped using Earth observations data and machine learning methods with good performance.

show abstract

“…The databases for each predictor variables are listed in Table 1. Detailed information about the databases Yang et al, 2013;Hengl et al, 2017;Sun et al, 2017;Ballabio et al, 2019 Net primary productivity NPP MODIS-NPP (MOD17A3; mean value during 2000-2014)…”

Section: Datasetsmentioning

confidence: 99%

Spatial Pattern and Environmental Drivers of Acid Phosphatase Activity in Europe

et al. 2020

View full text Add to dashboard Cite

Acid phosphatase produced by plants and microbes plays a fundamental role in the recycling of soil phosphorus (P). A quantification of the spatial variation in potential acid phosphatase activity (AP) on large spatial scales and its drivers can help to reduce the uncertainty in our understanding of bio-availability of soil P. We applied two machine-learning methods (Random forests and back-propagation artificial networks) to simulate the spatial patterns of AP across Europe by scaling up 126 site observations of potential AP activity from field samples measured in the laboratory, using 12 environmental drivers as predictors. The back-propagation artificial network (BPN) method explained 58% of AP variability, more than the regression tree model (49%). In addition, BPN was able to identify the gradients in AP along three transects in Europe. Partial correlation analysis revealed that soil nutrients (total nitrogen, total P, and labile organic P) and climatic controls (annual precipitation, mean annual temperature, and temperature amplitude) were the dominant factors influencing AP variations in space. Higher AP occurred in regions with higher mean annual temperature, precipitation and higher soil total nitrogen. Soil TP and Po were non-monotonically correlated with modeled AP for Europe, indicating diffident strategies of P utilization by biomes in arid and humid area. This study helps to separate the influences of each factor on AP production and to reduce the uncertainty in estimating soil P availability. The BPN model trained with European data, however, could not produce a robust global map of AP due to the lack of representative measurements of AP for tropical regions. Filling this data gap will help us to understand the physiological basis of P-use strategies in natural soils.

show abstract

Mapping LUCAS topsoil chemical properties at European scale using Gaussian process regression

Cited by 202 publications

References 53 publications

Understanding Fields by Remote Sensing: Soil Zoning and Property Mapping

Understanding Fields by Remote Sensing: Soil Zoning and Property Mapping

Mapping at 30 m Resolution of Soil Attributes at Multiple Depths in Midwest Brazil

Spatial Pattern and Environmental Drivers of Acid Phosphatase Activity in Europe

Contact Info

Product

Resources

About