scholarly journals Machine Learning With GA Optimization to Model the Agricultural Soil-Landscape of Germany: An Approach Involving Soil Functional Types With Their Multivariate Parameter Distributions Along the Depth Profile

2021 ◽  
Vol 9 ◽  
Author(s):  
Mareike Ließ ◽  
Anika Gebauer ◽  
Axel Don
Keyword(s):  
Machine Learning ◽  
Soil Properties ◽  
Depth Profile ◽  
Agricultural Soil ◽  
Soil Functions ◽  
National Scale ◽  
Soil Parameter ◽  
Functional Types ◽  
Soil Landscape ◽  
Soil Functionality

Societal demands on soil functionality in agricultural soil-landscapes are confronted with yield losses and environmental impact. Soil functional information at national scale is required to address these challenges. On behalf of the well-known theory that soils and their site-specific characteristics are the product of the interaction of the soil-forming factors, pedometricians seek to model the soil-landscape relationship using machine learning. Following the rationale that similarity in soils is reflected by similarity in landscape characteristics, we defined soil functional types (SFTs) which were projected into space by machine learning. Each SFT is described by a multivariate soil parameter distribution along its depth profile. SFTs were derived by employing multivariate similarity analysis on the dataset of the Agricultural Soil Inventory. Soil profiles were compared on behalf of differing sets of soil properties considering the top 100 and 200 cm, respectively. Various depth weighting coefficients were tested to attribute topsoil properties higher importance. Support vector machine (SVM) models were then trained employing optimization with a distributed multiple-population hybrid Genetic algorithm for parameter tuning. Model training, tuning, and evaluation were implemented in a nested k-fold cross-validation approach to avoid overfitting. With regards to the SFTs, organic soils were differentiated from mineral soils of various particle size distributions being partly influenced by waterlogging and groundwater. Further SFTs reflect soils with a depth limitation within the top 100 cm and high stone content. Altogether, with SVM predictive model accuracies between 0.7 and 0.9, the agricultural soil-landscape of Germany was represented with eight SFTs. Soil functionality with regards to the soil’s capacity to store plant-available water and soil organic carbon is well characterized. Four additional soil functions are described to a certain extent. An extension of the approach to fully cover soil functions such as nutrient cycling, agricultural biomass production, filtering of contaminants, and soil as a habitat for soil biota is possible with the inclusion of additional soil properties. Altogether, the developed data product represents the 3D multivariate soil parameter space. Its agglomerated simplicity into a limited number of spatially allocated process units provides the basis to run agricultural process models at national scale (Germany).

Volumetric soil quality modelling with machine learning in a diverse agricultural landscape in Andalusia, Spain

2020 ◽  
Author(s):  
Tobias Rentschler ◽  
Martin Bartelheim ◽  
Marta Díaz-Zorita Bonilla ◽  
Philipp Gries ◽  
Thomas Scholten ◽  
...  
Keyword(s):  
Machine Learning ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Soil Properties ◽  
Soil Quality ◽  
Three Dimensional ◽  
Soil Mapping ◽  
Soil Profiles ◽  
Soil Functions ◽  
Depth Functions

<p>Soils and soil functions are recognized as a key resource for human well-being throughout time. In an agricultural and forestry perspective, soil functions contribute to food and timber production. Other soil functions are related to freshwater security and energy provisioning. In general, the capacity of a soil to function within specific boundaries is summarised as soil quality. Knowledge about the spatial distribution of soil quality is crucial for sustainable land use and the protection of soils and their functions. This spatial knowledge can be obtained with accurate and efficient machine-learning-based soil mapping approaches, which allow the estimation of the soil quality at distinct locations. However, the vertical distribution of soil properties is usually neglected when assessing soil quality at distinct locations. To overcome such limitations, the depth function of soil properties needs to be incorporated in the modelling. This is not only important to get a better estimation of the overall soil quality throughout the rooting zone, but also to identify factors that limit plant growth, such as strong acidity or alkalinity, and the water holding capacity. Thus, the objective of this study was to model and map the soil quality indicators pH, soil organic carbon, sand, silt and clay content as a volumetric entity. The study area is located in southern Spain in the Province of Seville at the Guadalquivir river. It covers 1,000 km<sup>2</sup> of farmland, citrus and olive plantations, pastures and wood pasture (Dehesa) in the Sierra Morena mountain range, at the Guadalquivir flood plain and tertiary terraces. Soil samples were taken at 130 soil profiles in five depths (or less at shallow soils). The profiles were randomly stratified depending on slope position and land cover. We used a subset of 99 samples from representative soil profiles to assess the overall 513 samples with FT-IR spectroscopy and machine learning methods to model equal-area spline, polynomial and exponential depth functions for each soil quality indicator at each of the 130 profiles. These depth functions were modelled and predicted spatially with a comprehensive set of environmental covariates from remote sensing data, multi-scale terrain analysis and geological maps. By solving the spatially predicted depth functions with a vertical resolution of 5 cm, we obtained a volumetric, i.e. three-dimensional, map of pH, soil organic carbon content and soil texture. Preliminary results are promising for volumetric soil mapping and the estimation of soil quality and limiting factors in three-dimensional space.</p>

scholarly journals Effects of glyphosate-based herbicides and their active ingredients on earthworms, water infiltration and glyphosate leaching are influenced by soil properties

2021 ◽  
Vol 33 (1) ◽  
Author(s):  
Johann G. Zaller ◽  
Maureen Weber ◽  
Michael Maderthaner ◽  
Edith Gruber ◽  
Eszter Takács ◽  
...  
Keyword(s):  
Organic Matter ◽  
Soil Properties ◽  
Weed Control ◽  
Amaranthus Retroflexus ◽  
Water Infiltration ◽  
Soil Conditions ◽  
Soil Functions ◽  
Active Ingredients ◽  
Hand Weeding ◽  
Earthworm Activity

Abstract Background Glyphosate-based herbicides (GBHs) are among the most often used pesticides. The hundreds of GBHs used worldwide consist of the active ingredient (AI) glyphosate in form of different salts, possibly other AIs, and various mostly undisclosed co-formulants. Pesticide risk assessments are commonly performed using single AIs or GBHs at standard soil conditions without vegetation. In a greenhouse experiment, we established a weed population with common amaranth (Amaranthus retroflexus) to examine the effects of three GBHs (Roundup LB Plus, Roundup PowerFlex, Touchdown Quattro) and their corresponding AIs (salts of glyphosate isopropylammonium, potassium, diammonium) on the activity and physiological biomarkers (glutathione S-transferase, GST; acetylcholine esterase, AChE) of an ecologically relevant earthworm species (Lumbricus terrestris). GBHs and AIs were applied at recommended doses; hand weeding served as control. Experiments were established with two soil types differing in organic matter content (SOM; 3.0% vs. 4.1%) and other properties. Results Earthworm activity (casting and movement activity) decreased after application of glyphosate formulations or active ingredients compared to hand weeding. We found no consistent pattern that formulations had either higher or lower effects on earthworm activity than their active ingredients; rather, differences were substance-specific. Earthworm activity was little affected by soil organic matter levels. Biomarkers remained unaffected by weed control types; GST but not AChE was decreased under high SOM. Water infiltration after a simulated heavy rainfall was interactively affected by weed control types and SOM. Leachate amount was higher after application of formulations than active ingredients and was higher under low SOM. Glyphosate concentrations in soil and leachate were strongly affected by application of formulations or active ingredients and varied with SOM (significant weed control type x SOM interaction). Conclusions We found that both commercial formulations and pure active ingredients can influence earthworms with consequences on important soil functions. Glyphosate products showed increased, reduced or similar effects than pure glyphosate on particular soil functions; soil properties can substantially alter this. Especially at lower SOM, heavy rainfalls could lead to more glyphosate leaching into water bodies. A full disclosure of co-formulants would be necessary to further decipher their specific contributions to these inconsistent effects.

scholarly journals High resolution characterization of the soil organic carbon depth profile in a soil landscape affected by erosion

2016 ◽  
Vol 156 ◽  
pp. 185-193 ◽  
Author(s):  
Emilien Aldana Jague ◽  
Michael Sommer ◽  
Nicolas P.A. Saby ◽  
Jean-Thomas Cornelis ◽  
Bas Van Wesemael ◽  
...  
Keyword(s):  
High Resolution ◽  
Organic Carbon ◽  
Soil Organic Carbon ◽  
Depth Profile ◽  
Soil Landscape

scholarly journals Machine learning based soil maps for a wide range of soil properties for the forested area of Switzerland

2021 ◽  
pp. e00437
Author(s):  
Andri Baltensweiler ◽  
Lorenz Walthert ◽  
Marc Hanewinkel ◽  
Stephan Zimmermann ◽  
Madlene Nussbaum
Keyword(s):  
Machine Learning ◽  
Soil Properties ◽  
Soil Maps ◽  
Forested Area ◽  
Wide Range

Regional characterisation of soil properties by combining soil science and hyperspectral and thermal remote sensing: A technical overview of lab and field remote sensing methods

2021 ◽  
Author(s):  
Richard Mommertz ◽  
Lars Konen ◽  
Martin Schodlok
Keyword(s):  
Remote Sensing ◽  
Soil Properties ◽  
Regional Scale ◽  
Arable Land ◽  
Soil Mapping ◽  
Soil Science ◽  
Near Surface ◽  
Soil Parameter ◽  
The Impact ◽  
Parameter Retrieval

<p>Soil is one of the world’s most important natural resources for human livelihood as it provides food and clean water. Therefore, its preservation is of huge importance. For this purpose, a proficient regional database on soil properties is needed. The project “ReCharBo” (Regional Characterisation of Soil Properties) has the objective to combine remote sensing, geophysical and pedological methods to determine soil characteristics on a regional scale. Its aim is to characterise soils non-invasive, time and cost efficient and with a minimal number of soil samples to calibrate the measurements. Konen et al. (2021) give detailed information on the research concept and first field results in a presentation in the session “SSS10.3 Digital Soil Mapping and Assessment”. Hyperspectral remote sensing is a powerful and well known technique to characterise near surface soil properties. Depending on the sensor technology and the data quality, a wide variety of soil properties can be derived with remotely sensed data (Chabrillat et al. 2019, Stenberg et al. 2010). The project aims to investigate the effects of up and downscaling, namely which detail of information is preserved on a regional scale and how a change in scales affects the analysis algorithms and the possibility to retrieve valid soil parameter information. Thus, e.g. laboratory and field spectroscopy are applied to gain information of samples and fieldspots, respectively. Various UAV-based sensors, e.g. thermal & hyperspectral sensors, are applied to study soil properties of arable land in different study areas at field scale. Finally, airborne (helicopter) hyperspectral data will cover the regional scale. Additionally forthcoming spaceborne hyperspectral satellite data (e.g. Prisma, EnMAP, Sentinel-CHIME) are a promising outlook to gain detailed regional soil information. In this context it will be discussed how the multisensor data acquisition is best managed to optimise soil parameter retrieval. Sensor specific properties regarding time and date of acquisition as well as weather/atmospheric conditions are outlined. The presentation addresses and discusses the impact of a multisensor and multiscale remote sensing data collection regarding the results on soil parameter retrieval.</p><p> </p><p>References</p><p>Chabrillat, S., Ben-Dor, E. Cierniewski, J., Gomez, C., Schmid, T. & van Wesemael, B. (2019): Imaging Spectroscopy for Soil Mapping and Monitoring. Surveys in Geophysics 40:361–399. https://doi.org/10.1007/s10712-019-09524-0</p><p>Stenberg, B., Viscarra Rossel, R. A., Mounem Mouazen, A. & Wetterlind, J. (2010): Visible and Near Infrared Spectroscopy in Soil Science. In: Donald L. Sparks (editor): Advances in Agronomy. Vol. 107. Academic Press:163-215. http://dx.doi.org/10.1016/S0065-2113(10)07005-7</p>

scholarly journals Leveraging machine learning to produce a cost-effective national building height map of Ireland

2021 ◽  
Author(s):  
Eoghan Keany ◽  
Geoffrey Bessardon ◽  
Emily Gleeson
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
High Resolution ◽  
Land Cover ◽  
Urban Areas ◽  
Cost Effective ◽  
Land Cover Classification ◽  
National Scale ◽  
Building Height ◽  
Height Data

<p>To represent surface thermal, turbulent and humidity exchanges, Numerical Weather Prediction (NWP) systems require a land-cover classification map to calculate sur-face parameters used in surface flux estimation. The latest land-cover classification map used in the HARMONIE-AROME configuration of the shared ALADIN-HIRLAMNWP system for operational weather forecasting is ECOCLIMAP-SG (ECO-SG). The first evaluation of ECO-SG over Ireland suggested that sparse urban areas are underestimated and instead appear as vegetation areas (1). While the work of (2) on land-cover classification helps to correct the horizontal extent of urban areas, the method does not provide information on the vertical characteristics of urban areas. ECO-SG urban classification implicitly includes building heights (3), and any improvement to ECO-SG urban area extent requires a complementary building height dataset.</p><p>Openly accessible building height data at a national scale does not exist for the island of Ireland. This work seeks to address this gap in availability by extrapolating the preexisting localised building height data across the entire island. The study utilises information from both the temporal and spatial dimensions by creating band-wise temporal aggregation statistics from morphological operations, for both the Sentinel-1A/B and Sentinel-2A/B constellations (4). The extrapolation uses building height information from the Copernicus Urban Atlas, which contains regional coverage for Dublin at 10 m x10 m resolution (5). Various regression models were then trained on these aggregated statistics to make pixel-wise building height estimates. These model estimates were then evaluated with an adjusted RMSE metric, with the most accurate model chosen to map the entire country. This method relies solely on freely available satellite imagery and open-source software, providing a cost-effective mapping service at a national scale that can be updated more frequently, unlike expensive once-off private mapping services. Furthermore, this process could be applied by these services to reduce costs by taking a small representative sample and extrapolating the rest of the area. This method can be applied beyond national borders providing a uniform map that does not depends on the different private service practices facilitating the updates of global or continental land-cover information used in NWP.</p><p> </p><p>(1) G. Bessardon and E. Gleeson, “Using the best available physiography to improve weather forecasts for Ireland,” in Challenges in High-Resolution Short Range NWP at European level including forecaster-developer cooperation, European Meteorological Society, 2019.</p><p>(2) E. Walsh, et al., “Using machine learning to produce a very high-resolution land-cover map for Ireland, ” Advances in Science and Research,  (accepted for publication).</p><p>(3) CNRM, "Wiki - ECOCLIMAP-SG" https://opensource.umr-cnrm.fr/projects/ecoclimap-sg/wiki</p><p>(4) D. Frantz, et al., “National-scale mapping of building height using sentinel-1 and sentinel-2 time series,” Remote Sensing of Environment, vol. 252, 2021.</p><p>(5) M. Fitrzyk, et al., “Esa Copernicus sentinel-1 exploitation activities,” in IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium, IEEE, 2019.</p>

scholarly journals Estimation of Soil Cohesion Using Machine Learning Method: A Random Forest Approach

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Hai-Bang Ly ◽  
Thuy-Anh Nguyen ◽  
Binh Thai Pham
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Soil Properties ◽  
Clay Content ◽  
Absolute Error ◽  
Experimental Methods ◽  
Liquid Limit ◽  
Support Vector ◽  
Data Set ◽  
Soil Cohesion

Soil cohesion (C) is one of the critical soil properties and is closely related to basic soil properties such as particle size distribution, pore size, and shear strength. Hence, it is mainly determined by experimental methods. However, the experimental methods are often time-consuming and costly. Therefore, developing an alternative approach based on machine learning (ML) techniques to solve this problem is highly recommended. In this study, machine learning models, namely, support vector machine (SVM), Gaussian regression process (GPR), and random forest (RF), were built based on a data set of 145 soil samples collected from the Da Nang-Quang Ngai expressway project, Vietnam. The database also includes six input parameters, that is, clay content, moisture content, liquid limit, plastic limit, specific gravity, and void ratio. The performance of the model was assessed by three statistical criteria, namely, the correlation coefficient (R), mean absolute error (MAE), and root mean square error (RMSE). The results demonstrated that the proposed RF model could accurately predict soil cohesion with high accuracy (R = 0.891) and low error (RMSE = 3.323 and MAE = 2.511), and its predictive capability is better than SVM and GPR. Therefore, the RF model can be used as a cost-effective approach in predicting soil cohesion forces used in the design and inspection of constructions.

scholarly journals The effects of sealing on urban soil carbon and nutrients

SOIL ◽  
2021 ◽  
Vol 7 (2) ◽  
pp. 661-675
Author(s):  
Roisin O'Riordan ◽  
Jess Davies ◽  
Carly Stevens ◽  
John N. Quinton
Keyword(s):  
Ecosystem Services ◽  
Soil Properties ◽  
Soil Carbon ◽  
Urban Soil ◽  
Green Space ◽  
Great Influence ◽  
Nitrate Content ◽  
Soil Functions ◽  
Soil Sealing ◽  
Nutrient Stocks

Abstract. Urban soils are of increasing interest for their potential to provide ecosystem services such as carbon storage and nutrient cycling. Despite this, there is limited knowledge on how soil sealing with impervious surfaces, a common disturbance in urban environments, affects these important ecosystem services. In this paper, we investigate the effect of soil sealing on soil properties, soil carbon and soil nutrient stocks. We undertook a comparative survey of sealed and unsealed green space soils across the UK city of Manchester. Our results reveal that the context of urban soil and the anthropogenic artefacts added to soil have a great influence on soil properties and functions. In general, sealing reduced soil carbon and nutrient stocks compared to green space soil; however, where there were anthropogenic additions of organic and mineral artefacts, this led to increases in soil carbon and nitrate content. Anthropogenic additions led to carbon stocks equivalent to or larger than those in green spaces; this was likely a result of charcoal additions, leading to carbon stores with long residence times. This suggests that in areas with an industrial past, anthropogenic additions can lead to a legacy carbon store in urban soil and make important contributions to urban soil carbon budgets. These findings shed light on the heterogeneity of urban sealed soil and the influence of anthropogenic artefacts on soil functions. Our research highlights the need to gain a further understanding of urban soil processes, in both sealed and unsealed soils, and of the influence and legacy of anthropogenic additions for soil functions and important ecosystem services.

scholarly journals Cropping system effects on soil quality in the Great Plains: Synthesis from a regional project

2006 ◽  
Vol 21 (1) ◽  
pp. 49-59 ◽  
Author(s):  
B.J. Wienhold ◽  
J.L. Pikul ◽  
M.A. Liebig ◽  
M.M. Mikha ◽  
G.E. Varvel ◽  
...  
Keyword(s):  
Organic Matter ◽  
Soil Properties ◽  
Great Plains ◽  
Management Practices ◽  
Assessment Tool ◽  
Soil Management ◽  
Assessment Tools ◽  
Soil Functions ◽  
Organic C ◽  
Environmental Function

AbstractSoils perform a number of essential functions affecting management goals. Soil functions were assessed by measuring physical, chemical, and biological properties in a regional assessment of conventional (CON) and alternative (ALT) management practices at eight sites within the Great Plains. The results, reported in accompanying papers, provide excellent data for assessing how management practices collectively affect agronomic and environmental soil functions that benefit both farmers and society. Our objective was to use the regional data as an input for two new assessment tools to evaluate their potential and sensitivity for detecting differences (aggradation or degradation) in management systems. The soil management assessment framework (SMAF) and the agro-ecosystem performance assessment tool (AEPAT) were used to score individual soil properties at each location relative to expected conditions based on inherent soil-forming factors and to compute index values that provide an overall assessment of the agronomic and environmental impact of the CON and ALT practices. SMAF index values were positively correlated with grain yield (an agronomic function) and total organic matter (an agronomic and environmental function). They were negatively correlated with soil nitrate concentration at harvest (an indicator of environmental function). There was general agreement between the two assessment tools when used to compare management practices. Users can measure a small number of soil properties and use one of these tools to easily assess the effectiveness of soil management practices. A higher score in either tool identifies more environmentally and agronomically sustainable management. Temporal variability in measured indicators makes dynamic assessments of management practices essential. Water-filled pore space, aggregate stability, particulate organic matter, and microbial biomass were sensitive to management and should be included in studies aimed at improving soil management. Reductions in both tillage and fallow combined with crop rotation has resulted in improved soil function (e.g., nutrient cycling, organic C content, and productivity) throughout the Great Plains.

Sign in / Sign up

Export Citation Format

Share Document