Machine learning for digital soil mapping: Applications, challenges and suggested solutions

Wadoux, Alexandre M.J.‐C.; Minasny, Budiman; McBratney, Alex B.

doi:10.1016/j.earscirev.2020.103359

Cited by 338 publications

(185 citation statements)

References 185 publications

Supporting

Mentioning

182

Contrasting

Order By: Relevance

“…We used the general least square approach rather than a machine learning approach in order to explain the relationships between the explanatory variables and the explained variables, with information about the statistical significance and the signs of the relationships, while machine learning algorithms are better suited to provide accurate predictions (Wadoux et al 2020). We have standardized the variables to ease the comparison and the interpretation of the statistical analysis.…”

Section: Discussionmentioning

confidence: 99%

Spreading herbivore manure in livestock farms increases soil carbon content, while granivore manure decreases it

Curien

Issanchou

Degan

et al. 2021

Agron. Sustain. Dev.

View full text Add to dashboard Cite

Livestock farming occupies 57% of agricultural area in France and has contrasting impacts on the environment. Studies have analyzed relations between livestock farming and soil organic carbon (SOC) content, but the influence of livestock farming on soils is difficult to perceive at a large scale. The objective of this study was to increase understanding of impacts of livestock farming on soils that receive livestock manure depending on different initial levels of SOC content, at cantonal level. To this end, we used French soil and agricultural databases to analyze relations between livestock farming practices and SOC content. We used statistical data calculated from the French soil test database for the periods 2000–2004 and 2010–2014. For livestock farming practices, we used data from the French agricultural census of 2000 and 2010, and for spreading of livestock manure, data from the French program to control pollution of agricultural origin (2002–2007) and data from the French Livestock Institute. The novelty of our large-scale analysis is to differentiate the origin of livestock manure (herbivore or granivore) and the type of crop on which it was spread (crops or grasslands). Statistical analysis was performed at the cantonal scale for France using the method of generalized least squares. We show for the first time that, at the national scale, spreading of livestock manure influences SOC content and dynamics significantly. Our results also show the importance of the nature of the manure; solid manure increases SOC content, unlike liquid manure. Spreading herbivore manure on crops increases SOC content, but spreading granivore manure may decrease it. Livestock manure spread on grasslands has no significant effect on SOC content, possibly due to under-representation of grassland soils in the soil database. These results demonstrate the importance of the complementary between crop and livestock to maintain soil ecosystem services, including soil fertility.

show abstract

Section: Discussionmentioning

confidence: 99%

Spreading herbivore manure in livestock farms increases soil carbon content, while granivore manure decreases it

Curien

Issanchou

Degan

et al. 2021

Agron. Sustain. Dev.

View full text Add to dashboard Cite

show abstract

“…Machine learning (ML) is a large class of non-linear data-driven algorithms employed mainly for pattern recognition, data mining, and regression tasks. ML algorithms do not require certain assumptions (e.g., normal distribution) as opposed to statistical approaches [26]. Therefore, ML is increasingly used for monitoring and mapping agricultural systems [26][27][28][29][30][31][32][33][34][35][36][37][38].…”

Section: Referencesmentioning

confidence: 99%

Combining Remote Sensing and Meteorological Data for Improved Rice Plant Potassium Content Estimation

Eitel

Jennewein

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Potassium (K) plays a significant role in the formation of crop quality and yield. Accurate estimation of plant potassium content using remote sensing (RS) techniques is therefore of great interest to better manage crop K nutrition. To improve RS of crop K, meteorological information might prove useful, as it is well established that weather conditions affect crop K uptake. We aimed to determine whether including meteorological data into RS-based models can improve K estimation accuracy in rice (Oryza sativa L.). We conducted field experiments throughout three growing seasons (2017–2019). During each year, different treatments (i.e., nitrogen, potassium levels and plant varieties) were applied and spectra were taken at different growth stages throughout the growing season. Firstly, we conducted a correlation analysis between rice plant potassium content and transformed spectra (reflectance spectra (R), first derivative spectra (FD) and reciprocal logarithm-transformed spectra (log [1/R])) to select correlation bands. Then, we performed the genetic algorithms partial least-squares and linear mixed effects model to select important bands (IBs) and important meteorological factors (IFs) from correlation bands and meteorological data (daily average temperature, humidity, etc.), respectively. Finally, we used the spectral index and machine learning methods (partial least-squares regression (PLSR) and random forest (RF)) to construct rice plant potassium content estimation models based on transformed spectra, transformed spectra + IFs and IBs, and IBs + IFs, respectively. Results showed that normalized difference spectral index (NDSI (R1210, R1105)) had a moderate estimation accuracy for rice plant potassium content (R2 = 0.51; RMSE = 0.49%) and PLSR (FD-IBs) (R2 = 0.69; RMSE = 0.37%) and RF (FD-IBs) (R2 = 0.71; RMSE = 0.40%) models based on FD could improve the prediction accuracy. Among the meteorological factors, daily average temperature contributed the most to estimating rice plant potassium content, followed by daily average humidity. The estimation accuracy of the optimal rice plant potassium content models was improved by adding meteorological factors into the three RS models, with model R2 increasing to 0.65, 0.74, and 0.76, and RMSEs decreasing to 0.42%, 0.35%, and 0.37%, respectively, suggesting that including meteorological data can improve our ability to remotely sense plant potassium content in rice.

show abstract

“…Thus, in most cases, a more accurate prediction can be gained by a complex and complicated model than by a simple and easily interpretable one. However, we should try to understand these models as far as possible [73], e.g., by the application of post-hoc techniques [74,75]. The importance plot derived from a RF model can be a valuable tool trying to do so.…”

Section: On the Interpretability Of Machine Learning Algorithmsmentioning

confidence: 99%

Elaborating Hungarian Segment of the Global Map of Salt-Affected Soils (GSSmap): National Contribution to an International Initiative

et al. 2020

View full text Add to dashboard Cite

Recently, the Global Map of Salt-affected Soils (GSSmap) was launched, which pursued a country-driven approach and aimed to update the global and country-level information on salt-affected soils (SAS). The aim of this paper was to present how Hungary contributed to GSSmap by preparing its own SAS maps using advanced digital soil mapping techniques. We used not just a combination of random forest and multivariate geostatistical techniques for predicting the spatial distribution of SAS indicators (i.e., pH, electrical conductivity and exchangeable sodium percentage) for the topsoil (0–30 cm) and subsoil (30–100 cm), but also a number of indices derived from Sentinel-2 satellite images as environmental covariates. The importance plots of random forests showed that in addition to climatic, geomorphometric parameters and legacy soil information, image indices were the most important covariates. The performance of spatial modelling was checked by 10-fold cross validation showing that the accuracy of the SAS maps was acceptable. By this study and by the resulting maps of it, we not just contributed to GSSmap, but also renewed the SAS mapping methodology in Hungary, where we paid special attention to modelling and quantifying the prediction uncertainty that had not been quantified or even taken into consideration earlier.

show abstract

Machine learning for digital soil mapping: Applications, challenges and suggested solutions

Cited by 338 publications

References 185 publications

Spreading herbivore manure in livestock farms increases soil carbon content, while granivore manure decreases it

Spreading herbivore manure in livestock farms increases soil carbon content, while granivore manure decreases it

Combining Remote Sensing and Meteorological Data for Improved Rice Plant Potassium Content Estimation

Elaborating Hungarian Segment of the Global Map of Salt-Affected Soils (GSSmap): National Contribution to an International Initiative

Contact Info

Product

Resources

About