The Experts below are selected from a list of 43353 Experts worldwide ranked by ideXlab platform
Bas Van Wesemael - One of the best experts on this subject based on the ideXlab platform.
-
Imaging Spectroscopy for Soil Mapping and Monitoring
Surveys in Geophysics, 2019Co-Authors: Simon Chabrillat, Eyal Ben-dor, Jerzy Cierniewski, T. Schmid, C Gomez, Bas Van WesemaelAbstract:There is a renewed awareness of the finite nature of the world’s Soil resources, growing concern about Soil security and significant uncertainties about the carrying capacity of the planet. Regular assessments of Soil conditions from local through to global scales are requested, and there is a clear demand for accurate, up-to-date and spatially referenced Soil information by the modelling scientific community, farmers and land users, and policy- and decision-makers. Soil and imaging spectroscopy, based on visible–near-infrared and shortwave infrared (400–2500 nm) spectral reflectance, has been shown to be a proven method for the quantitative prediction of key Soil surface properties. With the upcoming launch of the next generation of hyperspectral satellite sensors in the next years, a high potential to meet the demand for global Soil Mapping and monitoring is appearing. In this paper, we briefly review the basic concepts of Soil spectroscopy with a special attention to the effects of Soil roughness on reflectance and then provide a review of state of the art, achievements and perspectives in Soil Mapping and monitoring based on imaging spectroscopy from air- and spaceborne sensors. Selected application cases are presented for the modelling of Soil organic carbon, mineralogical composition, topSoil water content and characterization of Soil crust, Soil erosion and Soil degradation stages based on airborne and simulated spaceborne imaging spectroscopy data. Further, current challenges, gaps and new directions toward enhanced Soil properties modelling are presented. Overall, this paper highlights the potential and limitations of multiscale imaging spectroscopy nowadays for Soil Mapping and monitoring, and capabilities and requirements of upcoming spaceborne sensors as support for a more informed and sustainable use of our world’s Soil resources.
Alex B. Mcbratney - One of the best experts on this subject based on the ideXlab platform.
-
Game theory interpretation of digital Soil Mapping convolutional neural networks
SOIL, 2020Co-Authors: José Padarian, Alex B. Mcbratney, Budiman MinasnyAbstract:Abstract. The use of complex models such as deep neural networks has yielded large improvements in predictive tasks in many fields including digital Soil Mapping. One of the concerns about using these models is that they are perceived as black boxes with low interpretability. In this paper we introduce the use of game theory, specifically Shapley additive explanations (SHAP) values, in order to interpret a digital Soil Mapping model. SHAP values represent the contribution of a covariate to the final model predictions. We applied this method to a multi-task convolutional neural network trained to predict Soil organic carbon in Chile. The results show the contribution of each covariate to the model predictions in three different contexts: (a) at a local level, showing the contribution of the various covariates for a single prediction; (b) a global understanding of the covariate contribution; and (c) a spatial interpretation of their contributions. The latter constitutes a novel application of SHAP values and also the first detailed analysis of a model in a spatial context. The analysis of a SOC (Soil organic carbon) model in Chile corroborated that the model is capturing sensible relationships between SOC and rainfall, temperature, elevation, slope, and topographic wetness index. The results agree with commonly reported relationships, highlighting environmental thresholds that coincide with significant areas within the study area. This contribution addresses the limitations of the current interpretation of models in digital Soil Mapping, especially in a spatial context. We believe that SHAP values are a valuable tool that should be included within the DSM (digital Soil Mapping) framework, since they address the important concerns regarding the interpretability of more complex models. The model interpretation is a crucial step that could lead to generating new knowledge to improve our understanding of Soils.
-
Game theory interpretation of digital Soil Mapping convolutional neural networks
2020Co-Authors: José Padarian, Alex B. Mcbratney, Budiman MinasnyAbstract:Abstract. The use of complex models such as deep neural networks has yielded large improvements in predictive tasks in many fields including digital Soil Mapping. Once of the concerns about using these models is that they are perceived as black boxes with low interpretability. In this paper we introduce the use of game theory, specifically SHAP values, in order to interpret a digital Soil Mapping model. SHAP values represent the contribution of a covariate to the final model predictions. We applied this method to a multi-task convolutional neural network trained to predict Soil organic carbon of Chile. The results show the contribution of each covariate to the model predictions in three different contexts: (a) at a local level, showing the contribution of the various covariates for a single prediction, (b) a global understanding of the covariate contribution, and (c) a spatial interpretation of their contributions. The latter constitutes a novel application of SHAP values and also the first detailed analysis of a model in a spatial context. The analysis of a SOC model in Chile corroborated that the model is capturing sensible relationships between SOC and rainfall, temperature, elevation, slope and topographic wetness index. The results agree with commonly reported relationships, highlighting environmental thresholds that coincide with significant areas within the study area. This contribution addresses the limitations of the current interpretation of models in digital Soil Mapping, especially in a spatial context. We believe that SHAP values are a valuable tool that should be included within the DSM framework since they address the important concerns regarding the interpretability of more complex models. The model interpretation is a crucial step that could lead to generating new knowledge to improve our understanding of Soils.
-
Pedology and digital Soil Mapping (DSM)
European Journal of Soil Science, 2019Co-Authors: Budiman Minasny, Brendan P. Malone, Alex B. McbratneyAbstract:Pedology focuses on understanding Soil genesis in the field and includes Soil classification and Mapping. Digital Soil Mapping (DSM) has evolved from traditional Soil classification and Mapping to the creation and population of spatial Soil information systems by using field and laboratory observations coupled with environmental covariates. Pedological knowledge of Soil distribution and processes can be useful for digital Soil Mapping. Conversely, digital Soil Mapping can bring new insights to pedogenesis, detailed information on vertical and lateral Soil variation, and can generate research questions that were not considered in traditional pedology. This review highlights the relevance and synergy of pedology in Soil spatial prediction through the expansion of pedological knowledge. We also discuss how DSM can support further advances in pedology through improved representation of spatial Soil information. Some major findings of this review are as follows: (a) Soil classes can be mapped accurately using DSM, (b) the occurrence and thickness of Soil horizons, whole Soil profiles and Soil parent material can be predicted successfully with DSM techniques, (c) DSM can provide valuable information on pedogenic processes (e.g. addition, removal, transformation and translocation), (d) pedological knowledge can be incorporated into DSM, but DSM can also lead to the discovery of knowledge, and (e) there is the potential to use process‐based Soil–landscape evolution modelling in DSM. Based on these findings, the combination of data‐driven and knowledge‐based methods promotes even greater interactions between pedology and DSM. HIGHLIGHTS: Demonstrates relevance and synergy of pedology in Soil spatial prediction, and links pedology and DSM. Indicates the successful application of DSM in Mapping Soil classes, profiles, pedological features and processes. Shows how DSM can help in forming new hypotheses and gaining new insights about Soil and Soil processes. Combination of data‐driven and knowledge‐based methods recommended to promote greater interactions between DSM and pedology.
-
Using deep learning for Digital Soil Mapping
2018Co-Authors: José Padarian, Budiman Minasny, Alex B. McbratneyAbstract:Abstract. Digital Soil Mapping has been widely used as a cost-effective method for generating Soil maps. However, current DSM data representation rarely incorporates contextual information of the landscape. DSM models are usually calibrated using point observations intersected with spatially corresponding point covariates. Here, we demonstrate the use of the convolutional neural network model that incorporates contextual information surrounding an observation to significantly improve the prediction accuracy over conventional DSM models. We describe a convolutional neural network (CNN) model that takes inputs as images of covariates and explores spatial contextual information by finding non-linear local spatial relationships of neighbouring pixels. Unique features of the proposed model include: input represented as 3D stack of images, data augmentation to reduce overfitting, and simultaneously predicting multiple outputs. Using a Soil Mapping example in Chile, the CNN model was trained to simultaneously predict Soil organic carbon at multiples depths across the country. The results showed the CNN model reduced the error by 30 % compared with conventional techniques that only used point information of covariates. In the example of country-wide Mapping at 100 m resolution, the neighbourhood size from 3 to 9 pixels is more effective than at a point location and larger neighbourhood sizes. In addition, the CNN model produces less prediction uncertainty and it is able to predict Soil carbon at deeper Soil layers more accurately. Because the CNN model takes covariate represented as images, it offers a simple and effective framework for future DSM models.
-
GlobalSoilMap: Digital Soil Mapping from Country to Globe
2018Co-Authors: Dominique Arrouays, Igor Savin, Johan G.b. Leenaars, Alex B. McbratneyAbstract:GlobalSoilMap: Digital Soil Mapping from Country to Globe
Simon Chabrillat - One of the best experts on this subject based on the ideXlab platform.
-
Imaging Spectroscopy for Soil Mapping and Monitoring
Surveys in Geophysics, 2019Co-Authors: Simon Chabrillat, Eyal Ben-dor, Jerzy Cierniewski, T. Schmid, C Gomez, Bas Van WesemaelAbstract:There is a renewed awareness of the finite nature of the world’s Soil resources, growing concern about Soil security and significant uncertainties about the carrying capacity of the planet. Regular assessments of Soil conditions from local through to global scales are requested, and there is a clear demand for accurate, up-to-date and spatially referenced Soil information by the modelling scientific community, farmers and land users, and policy- and decision-makers. Soil and imaging spectroscopy, based on visible–near-infrared and shortwave infrared (400–2500 nm) spectral reflectance, has been shown to be a proven method for the quantitative prediction of key Soil surface properties. With the upcoming launch of the next generation of hyperspectral satellite sensors in the next years, a high potential to meet the demand for global Soil Mapping and monitoring is appearing. In this paper, we briefly review the basic concepts of Soil spectroscopy with a special attention to the effects of Soil roughness on reflectance and then provide a review of state of the art, achievements and perspectives in Soil Mapping and monitoring based on imaging spectroscopy from air- and spaceborne sensors. Selected application cases are presented for the modelling of Soil organic carbon, mineralogical composition, topSoil water content and characterization of Soil crust, Soil erosion and Soil degradation stages based on airborne and simulated spaceborne imaging spectroscopy data. Further, current challenges, gaps and new directions toward enhanced Soil properties modelling are presented. Overall, this paper highlights the potential and limitations of multiscale imaging spectroscopy nowadays for Soil Mapping and monitoring, and capabilities and requirements of upcoming spaceborne sensors as support for a more informed and sustainable use of our world’s Soil resources.
Budiman Minasny - One of the best experts on this subject based on the ideXlab platform.
-
Game theory interpretation of digital Soil Mapping convolutional neural networks
SOIL, 2020Co-Authors: José Padarian, Alex B. Mcbratney, Budiman MinasnyAbstract:Abstract. The use of complex models such as deep neural networks has yielded large improvements in predictive tasks in many fields including digital Soil Mapping. One of the concerns about using these models is that they are perceived as black boxes with low interpretability. In this paper we introduce the use of game theory, specifically Shapley additive explanations (SHAP) values, in order to interpret a digital Soil Mapping model. SHAP values represent the contribution of a covariate to the final model predictions. We applied this method to a multi-task convolutional neural network trained to predict Soil organic carbon in Chile. The results show the contribution of each covariate to the model predictions in three different contexts: (a) at a local level, showing the contribution of the various covariates for a single prediction; (b) a global understanding of the covariate contribution; and (c) a spatial interpretation of their contributions. The latter constitutes a novel application of SHAP values and also the first detailed analysis of a model in a spatial context. The analysis of a SOC (Soil organic carbon) model in Chile corroborated that the model is capturing sensible relationships between SOC and rainfall, temperature, elevation, slope, and topographic wetness index. The results agree with commonly reported relationships, highlighting environmental thresholds that coincide with significant areas within the study area. This contribution addresses the limitations of the current interpretation of models in digital Soil Mapping, especially in a spatial context. We believe that SHAP values are a valuable tool that should be included within the DSM (digital Soil Mapping) framework, since they address the important concerns regarding the interpretability of more complex models. The model interpretation is a crucial step that could lead to generating new knowledge to improve our understanding of Soils.
-
Game theory interpretation of digital Soil Mapping convolutional neural networks
2020Co-Authors: José Padarian, Alex B. Mcbratney, Budiman MinasnyAbstract:Abstract. The use of complex models such as deep neural networks has yielded large improvements in predictive tasks in many fields including digital Soil Mapping. Once of the concerns about using these models is that they are perceived as black boxes with low interpretability. In this paper we introduce the use of game theory, specifically SHAP values, in order to interpret a digital Soil Mapping model. SHAP values represent the contribution of a covariate to the final model predictions. We applied this method to a multi-task convolutional neural network trained to predict Soil organic carbon of Chile. The results show the contribution of each covariate to the model predictions in three different contexts: (a) at a local level, showing the contribution of the various covariates for a single prediction, (b) a global understanding of the covariate contribution, and (c) a spatial interpretation of their contributions. The latter constitutes a novel application of SHAP values and also the first detailed analysis of a model in a spatial context. The analysis of a SOC model in Chile corroborated that the model is capturing sensible relationships between SOC and rainfall, temperature, elevation, slope and topographic wetness index. The results agree with commonly reported relationships, highlighting environmental thresholds that coincide with significant areas within the study area. This contribution addresses the limitations of the current interpretation of models in digital Soil Mapping, especially in a spatial context. We believe that SHAP values are a valuable tool that should be included within the DSM framework since they address the important concerns regarding the interpretability of more complex models. The model interpretation is a crucial step that could lead to generating new knowledge to improve our understanding of Soils.
-
Pedology and digital Soil Mapping (DSM)
European Journal of Soil Science, 2019Co-Authors: Budiman Minasny, Brendan P. Malone, Alex B. McbratneyAbstract:Pedology focuses on understanding Soil genesis in the field and includes Soil classification and Mapping. Digital Soil Mapping (DSM) has evolved from traditional Soil classification and Mapping to the creation and population of spatial Soil information systems by using field and laboratory observations coupled with environmental covariates. Pedological knowledge of Soil distribution and processes can be useful for digital Soil Mapping. Conversely, digital Soil Mapping can bring new insights to pedogenesis, detailed information on vertical and lateral Soil variation, and can generate research questions that were not considered in traditional pedology. This review highlights the relevance and synergy of pedology in Soil spatial prediction through the expansion of pedological knowledge. We also discuss how DSM can support further advances in pedology through improved representation of spatial Soil information. Some major findings of this review are as follows: (a) Soil classes can be mapped accurately using DSM, (b) the occurrence and thickness of Soil horizons, whole Soil profiles and Soil parent material can be predicted successfully with DSM techniques, (c) DSM can provide valuable information on pedogenic processes (e.g. addition, removal, transformation and translocation), (d) pedological knowledge can be incorporated into DSM, but DSM can also lead to the discovery of knowledge, and (e) there is the potential to use process‐based Soil–landscape evolution modelling in DSM. Based on these findings, the combination of data‐driven and knowledge‐based methods promotes even greater interactions between pedology and DSM. HIGHLIGHTS: Demonstrates relevance and synergy of pedology in Soil spatial prediction, and links pedology and DSM. Indicates the successful application of DSM in Mapping Soil classes, profiles, pedological features and processes. Shows how DSM can help in forming new hypotheses and gaining new insights about Soil and Soil processes. Combination of data‐driven and knowledge‐based methods recommended to promote greater interactions between DSM and pedology.
-
Using deep learning for Digital Soil Mapping
2018Co-Authors: José Padarian, Budiman Minasny, Alex B. McbratneyAbstract:Abstract. Digital Soil Mapping has been widely used as a cost-effective method for generating Soil maps. However, current DSM data representation rarely incorporates contextual information of the landscape. DSM models are usually calibrated using point observations intersected with spatially corresponding point covariates. Here, we demonstrate the use of the convolutional neural network model that incorporates contextual information surrounding an observation to significantly improve the prediction accuracy over conventional DSM models. We describe a convolutional neural network (CNN) model that takes inputs as images of covariates and explores spatial contextual information by finding non-linear local spatial relationships of neighbouring pixels. Unique features of the proposed model include: input represented as 3D stack of images, data augmentation to reduce overfitting, and simultaneously predicting multiple outputs. Using a Soil Mapping example in Chile, the CNN model was trained to simultaneously predict Soil organic carbon at multiples depths across the country. The results showed the CNN model reduced the error by 30 % compared with conventional techniques that only used point information of covariates. In the example of country-wide Mapping at 100 m resolution, the neighbourhood size from 3 to 9 pixels is more effective than at a point location and larger neighbourhood sizes. In addition, the CNN model produces less prediction uncertainty and it is able to predict Soil carbon at deeper Soil layers more accurately. Because the CNN model takes covariate represented as images, it offers a simple and effective framework for future DSM models.
-
Using Digital Soil Mapping to Update, Harmonize and Disaggregate Legacy Soil Maps
Using R for Digital Soil Mapping, 2016Co-Authors: Brendan P. Malone, Budiman Minasny, Alex B. McbratneyAbstract:Digital Soil maps are contrasted from legacy Soil maps mainly in terms of the underlying spatial data model. Digital Soil maps are based on the pixel data model, while legacy Soil maps will typically consist of a tessellation of polygons. The advantage of the pixel model is that the information is spatially explicit. The Soil map polygons are delineations of Soil Mapping units which consist of a defined assemblage of Soil classes assumed to exist in more-or-less fixed proportions. There is great value in legacy Soil Mapping because a huge amount of expertise and resources went into their creation. Digital Soil Mapping will be the richer by using this existing knowledge-base to derive detailed and high resolution digital Soil infrastructures. However the digitization of legacy Soil maps is not digital Soil Mapping. Rather, the incorporation of legacy Soil maps into a digital Soil Mapping workflow involves some method (usually quantitative) of data mining, to appoint spatially explicit Soil information—usually a Soil class or even a measurable Soil attribute—upon a grid the covers the extent of the existing (legacy) Mapping. In some ways, this process is akin to downscaling because there is a need to extract Soil class or attribute information from aggregated Soil Mapping units. A better term therefore is Soil map disaggregation.
Jerzy Cierniewski - One of the best experts on this subject based on the ideXlab platform.
-
Imaging Spectroscopy for Soil Mapping and Monitoring
Surveys in Geophysics, 2019Co-Authors: Simon Chabrillat, Eyal Ben-dor, Jerzy Cierniewski, T. Schmid, C Gomez, Bas Van WesemaelAbstract:There is a renewed awareness of the finite nature of the world’s Soil resources, growing concern about Soil security and significant uncertainties about the carrying capacity of the planet. Regular assessments of Soil conditions from local through to global scales are requested, and there is a clear demand for accurate, up-to-date and spatially referenced Soil information by the modelling scientific community, farmers and land users, and policy- and decision-makers. Soil and imaging spectroscopy, based on visible–near-infrared and shortwave infrared (400–2500 nm) spectral reflectance, has been shown to be a proven method for the quantitative prediction of key Soil surface properties. With the upcoming launch of the next generation of hyperspectral satellite sensors in the next years, a high potential to meet the demand for global Soil Mapping and monitoring is appearing. In this paper, we briefly review the basic concepts of Soil spectroscopy with a special attention to the effects of Soil roughness on reflectance and then provide a review of state of the art, achievements and perspectives in Soil Mapping and monitoring based on imaging spectroscopy from air- and spaceborne sensors. Selected application cases are presented for the modelling of Soil organic carbon, mineralogical composition, topSoil water content and characterization of Soil crust, Soil erosion and Soil degradation stages based on airborne and simulated spaceborne imaging spectroscopy data. Further, current challenges, gaps and new directions toward enhanced Soil properties modelling are presented. Overall, this paper highlights the potential and limitations of multiscale imaging spectroscopy nowadays for Soil Mapping and monitoring, and capabilities and requirements of upcoming spaceborne sensors as support for a more informed and sustainable use of our world’s Soil resources.
