LUCAS Soil, the largest expandable soil dataset for Europe: a review

Orgiazzi, Alberto; Ballabio, Cristiano; Panagos, Panos; Jones, Arwyn; Fernández‐Ugalde, Oihane

doi:10.1111/ejss.12499

Cited by 414 publications

(250 citation statements)

References 40 publications

(35 reference statements)

Supporting

Mentioning

246

Contrasting

Unclassified

Order By: Relevance

“…A consistent amount of phosphorous (P) is also displaced with sediments (by water erosion) from the topsoil, where it is preferentially accumulated due to fertilisations and its low mobility. Considering the average content of available P from the LUCAS dataset (Orgiazzi, Ballabio, Panagos, Jones, & Fernández‐Ugalde, ), the erosion rates from RUSLE2015 and the price of P fertiliser (€440 as di‐ammonium phosphate; FAO, ), its substitution would cost €3–17 million per year. This wide range is related to the uncertain relation between plant uptake and available P from soil analysis; therefore, we considered (conservatively) that 10% to 50% of available P lost could be directly uptake by plants yearly.…”

Section: Resultsmentioning

confidence: 99%

Cost of agricultural productivity loss due to soil erosion in the European Union: From direct cost evaluation approaches to the use of macroeconomic models

et al. 2018

Self Cite

View full text Add to dashboard Cite

Much research has been carried out on modelling soil erosion rates under different climatic and land use conditions. Although some studies have addressed the issue of reduced crop productivity due to soil erosion, few have focused on the economic loss in terms of agricultural production and gross domestic product (GDP). In this study, soil erosion modellers and economists come together to carry out an economic evaluation of soil erosion in the European Union (EU). The study combines biophysical and macroeconomic models to estimate the cost of agricultural productivity loss due to soil erosion by water in the EU. The soil erosion rates, derived from the RUSLE2015 model, are used to estimate the loss in crop productivity (physical change in the production of plants) and to model their impact on the agricultural sector per country. A computable general equilibrium model is then used to estimate the impact of crop productivity change on agricultural production and GDP. The 12 million hectares of agricultural areas in the EU that suffer from severe erosion are estimated to lose around 0.43% of their crop productivity annually. The annual cost of this loss in agricultural productivity is estimated at around €1.25 billion. The computable general equilibrium model estimates the cost in the agricultural sector to be close to €300 million and the loss in GDP to be about €155 million. Italy emerges as the country that suffers the highest economic impact, whereas the agricultural sector in most Northern and Central European countries is only marginally affected by soil erosion losses. Soil erosion is the biggest threat to soil fertility and productivity, as it removes organic matter and important nutrients and prevents vegetation growth, which negatively affects overall biodiversity (Scherr, 2000). In particular, soil erosion changes the physical, chemical, and biological characteristics of soil, which leads to a drop in potential agricultural productivity and gives rise to concerns about food security, especially in the context of a growing world population (Food and Agriculture Organization [FAO], 2015a;Graves et al., 2015;Pimentel, 2006). ----------------------------------------------------------------This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Resultsmentioning

confidence: 99%

Cost of agricultural productivity loss due to soil erosion in the European Union: From direct cost evaluation approaches to the use of macroeconomic models

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, soil is an inherently complex material; therefore, models developed from one local region are inapplicable to another because the corresponding spectra can be quite dissimilar. To counter this, large soil spectral libraries (SSLs) have been developed over the past decade that cover national and continental scales (Orgiazzi, Ballabio, Panagos, Jones, & Fernández-Ugalde, 2018;Rossel & Webster, 2012;Shi, Ji, Viscarra Rossel, Chen, & Zhou, 2015;Wijewardane, Ge, Wills, & Loecke, 2016). One such approach was completed in 2017 from the GEO-CRADLE project, containing 1,753 soil samples from countries spanning the Balkans, the Middle East and North Africa.…”

mentioning

confidence: 99%

A genetic algorithm‐based stacking algorithm for predicting soil organic matter from vis–NIR spectral data

Tsakiridis

Tziolas

Theocharis

et al. 2019

European J Soil Science

View full text Add to dashboard Cite

It has been demonstrated that diffuse reflectance spectroscopy in the visible and near‐infrared (vis–NIR) can be exploited to predict chemical and physical soil properties. Immense soil spectral libraries (SSL) are being developed; therefore, more elaborate tools that capitalize on contemporary knowledge and techniques need to be established to provide accurate predictions. In this paper, we propose a novel genetic algorithm‐based stacking model that makes synergetic use of multiple models developed from different preprocessed spectral sources (termed L1 models). This is a form of ensemble learning where multiple hypotheses are combined to create a more robust and more accurate ensemble hypothesis. The genetic algorithm automatically defines the configuration of the stacked model, by selecting the best cooperating subset of the initial models. Our methodology was tested on the newly developed GEO‐CRADLE SSL to predict soil organic matter (SOM). Results showed that the accuracy of prediction of the proposed method ( R2 = 0.76, and ratio of performance to interquartile range [RPIQ] = 2.22) was better than the one attained by the best L1 model ( R2 = 0.65, RPIQ = 1.93). This approach can thus be effectively utilized to enhance the predictions of soil properties in small and large soil spectral libraries alike. Highlights A novel model stacking algorithm is proposed, combining spectral models from different sources and algorithms. Use of a genetic algorithm is examined, accounting for the large number of possible model permutations. The methodology was applied to the GEO‐CRADLE vis–NIR soil spectral library. Results indicate that model stacking creates more accurate and robust models.

show abstract

“…The spectral resolution of the applied sensor is 0.5 nm. The new 2018 dataset will include, among others, soil biodiversity properties and soil moisture data (Orgiazzi et al, 2018).…”

Section: The Lucas Datasetmentioning

confidence: 99%

Soil Texture Classification With 1d Convolutional Neural Networks Based on Hyperspectral Data

Riese

Keller

2019

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Soil texture is important for many environmental processes. In this paper, we study the classification of soil texture based on hyperspectral data. We develop and implement three 1-dimensional (1D) convolutional neural networks (CNN): the LucasCNN, the LucasResNet which contains an identity block as residual network, and the LucasCoordConv with an additional coordinates layer. Furthermore, we modify two existing 1D CNN approaches for the presented classification task. The code of all five CNN approaches is available on GitHub (Riese, 2019). We evaluate the performance of the CNN approaches and compare them to a random forest classifier. Thereby, we rely on the freely available LUCAS topsoil dataset. The CNN approach with the least depth turns out to be the best performing classifier. The LucasCoordConv achieves the best performance regarding the average accuracy. In future work, we can further enhance the introduced LucasCNN, LucasResNet and LucasCoordConv and include additional variables of the rich LUCAS dataset.

show abstract

LUCAS Soil, the largest expandable soil dataset for Europe: a review

Cited by 414 publications

References 40 publications

Cost of agricultural productivity loss due to soil erosion in the European Union: From direct cost evaluation approaches to the use of macroeconomic models

Cost of agricultural productivity loss due to soil erosion in the European Union: From direct cost evaluation approaches to the use of macroeconomic models

A genetic algorithm‐based stacking algorithm for predicting soil organic matter from vis–NIR spectral data

Soil Texture Classification With 1d Convolutional Neural Networks Based on Hyperspectral Data

Contact Info

Product

Resources

About