Explore the vast range of titles available.

Background and Aims To enhance Brazilian sugarcane production sustainably, crop simulation models have been utilized. However, due to the lack of reliable information, particularly concerning soil variability, these models have shown limited performance for specific analyses. This study aims to evaluate Digital Soil Mapping (DSM) as an alternative for filling soil data gaps in crop modeling and to assess the influence of these products on prediction uncertainties. The study site is located in Piracicaba region, Southern Brazil. Methods The framework was: (i) a legacy soil data were utilized, and equal-spline equations were applied to standardize the dataset.; (ii) a machine learning (ML) algorithm was used to predict soil attributes and their uncertainties; (iii) pedotransfer functions were applied to obtain soil hydrological properties; (iv) DSSAT/CANEGRO crop model was used to estimate sugarcane yield; (iv) a legacy soil map (LSM), SoilGrids (SG) and a map of attributes derived from regional DSM (RDSM) were compared; (v) a Monte Carlo Simulation (MCS) was conducted with the RDSM maps to evaluate the impact of uncertainties in the estimation of sugarcane yield. Results The DSM proved to be a reliable source for use in crop models, reaching similar results to field data. The sugarcane yield map emphasized the model’s sensitivity to soil attributes, with texture and depth significantly impacting yield estimations. Conclusion In this sense, coupling DSM and crop modeling is a feasible way to improve yield estimates, especially in countries with limited soil databases. Highlights • Crop simulation models have limited application due to the lack of soil data. • Digital Soil Mapping was coupled to a sugarcane simulation model to fill the gap of soil information. • Soil attributes and their uncertainties were predicted on a 250-m grid using machine learning algorithm. • A spatially-explicit DSSAT/CANEGRO model was able to represent variations in sugarcane yield at the regional scale; • Sugarcane yield was strongly affected by soil variability and its uncertainties; • Our finds indicate the importance of detailed soil databases and their impact on yield predictions. Graphical abstract

AbstractA series of soil salinization maps of the Ust’-Orda Buryat okrug of Irkutsk oblast on a scale of 1 : 300 000 was compiled for the first time on the basis of the GIS project in the ArcInfo environment. The maps enabled us to answer a number of questions about the distribution of saline and solonetzic soils and the chemical composition of salts. These maps were used to calculate the areas of salt-affected soils taking into account the depth and degree of salinization and the chemical composition of salts. The maps were compiled on the basis of a cross-analysis of 73 soil maps: 68 large-scale soil maps of farms on a scale of 1 : 25 000 for six districts of the okrug, two medium-scale soil maps of the okrug, and three small-scale soil maps, and two small-scale maps of soil salinization. The boundaries of mapping areas were delineated with due account for remote sensing data (RSD), topographic maps, and digital elevation model (SRTM). The compiled maps were verified using 136 georeferenced soil pits with analytical information on salinization. We identified 346 mapping areas containing different proportions of saline soils with a total area of 364 300 ha. Slightly saline soils sulfate salinization in the surface layer predominated. Sulfate salinization with gypsum and sulfate salinization with toxic alkalinity determined by magnesium bicarbonate were identified on the maps for the first time. Alkalinity associated with soda rarely occurs in soils with predominating alkaline sulfate–chloride salinization. Predominantly chloride salinization is also not widespread. Soils saline in the upper 1-m-thick layer occupy 45 200 ± 17 300 ha (slightly saline) and 17 800 ± 7900 ha (moderately and strongly saline), and the area of solonchaks is 4700 ± 2500 ha. The area of solonetzes is 2800 ± 2200 ha, and solonetzic soils occupy 25 100 ± 12 500 ha.

Soil surveying and mapping provide important support for environmental science research on soil and other resources. Due to the rapid change in land use and the long update cycle of soil maps, historical conventional soil maps (CSMs) may be outdated and have low accuracy. Therefore, there is an urgent need for accurate and up-to-date soil maps. Soil has a high correlation with its corresponding environmental factors in space, and typical samples contain an appropriate soil–environment relationship of soil types. Understanding how to extract typical samples according to environmental factors and determine the implied soil–environment relationship is the key to updating soil maps. In this study, a hierarchical typical sample extraction method based on land use type and environmental factors was designed. According to the corresponding relationship between the soil type and the land use type (ST-LU), the outdate soil map patches caused by changes in land use were excluded, follow by typical samples being extracted according to the peak intervals of the soil–environmental factor histograms. Additionally, feature selection was performed through variance analysis and mutual information, and four machine learning models were used to predict soil types. In addition, the influence of environmental factors on soil prediction was discussed, in terms of variable importance analysis. Using an overall common validation set, the results show that the prediction accuracy using typical samples for learning in the modeling set is above 0.8, while the prediction accuracy when using random samples is only about 0.4. Compared with the original soil map, the accuracy and resolution of the predicted soil maps based on typical samples are greatly improved. In general, typical samples can effectively explore the actual soil–environment knowledge implied in the soil type map. By extracting typical samples from historical soil type map and combining them with high-resolution remote sensing data, we can generate new soil type maps with high accuracy and short update cycle. This can provide some references for typical sampling design and soil type prediction.

Soils provide habitat, regulation and utilization functions. Therefore, Germany aims to reduce soil sealing to 30 ha day - 1 by 2030 and to eliminate it by 2050. About 55 ha day - 1 of soil are damaged (average 2018–2021), but detailed information on its soil quality is lacking. This study proposes a new approach using geo-information and remote sensing data to assess agricultural soil loss in Lower Saxony and Brandenburg. Soil quality is assessed based on erosion resistance, runoff regulation, filter functions, yield potential and the Müncheberg Soil Quality Rating from 2006 to 2015. Data from the German Soil Map at a scale of 1:200,000 (BÜK 200), climate, topography, CORINE Land Cover (CLC) and Imperviousness Layer (IMCC), both provided by the Copernicus Land Monitoring Service (CLMS), are used to generate information on soil functions, potentials and agricultural soil loss due to sealing. For the first time, soil losses under arable land are assessed spatially, quantitatively and qualitatively. An estimate of the qualitative loss of agricultural soil in Germany between 2006 and 2015 is obtained by intersecting the soil evaluation results with the quantitative soil loss according to IMCC. Between 2006 and 2015, about 73,300 ha of land were sealed in Germany, affecting about 37,000 ha of agricultural soils. This corresponds to a sealing rate of 11 ha per day for Germany. In Lower Saxony and Brandenburg, agricultural soils were sealed at a rate of 1.9 ha day - 1 and 0.8 ha day - 1 respectively, removing these soils from primary land use. In Lower Saxony, 75% of soils with moderate or better biotic yield potential have been removed from primary land use, while in Brandenburg this figure is as high as 88%. Implementing this approach can help decision-makers reassess sealed land and support Germany’s sustainable development strategy.

Hillslope elements and land cover types are primarily determining the spatial variability of soils in the hilly and mountainous landscape. Among the soil forming factors, topography strongly influences pedogenic process and governs the variability of soils in hilly and mountainous landscape. This study mainly focusses on characterizing soil quality parameters distribution based on the hillslope elements and soil–landscape units in the watershed. Digital terrain model (DTM)-derived topographic position index was used to delineate various hillslope elements. Land use/land cover map was generated using random forest machine learning technique. Hillslope elements, land use/land cover types and aspects were integrated in GIS environment to generate soil–landscape unit map of the watershed. Soil samples were collected based on various soil–landscape units to characterize soil quality parameters such as total carbon (TC) soil organic matter (SOM), total nitrogen (TN), aggregate stability (SAS) in the watershed. SOM ranged from 1.6% to 10.05% and higher estimated in shoulder (forest) followed by valley (agriculture) and toe slope (forest). TC and TN contents ranged from 0.93% to 5.84% and 0.11% to 0.38%, respectively. The C:N ratio ranged from 7.96% to 18.31% and high value was found in shoulder (forest) followed by valley (agriculture) and toe slope (forest). SAS under different hillslope elements in the area ranged from 0.0.552 to 0.615 indicating large spatial variation of soil quality parameters. The study indicates that in hilly and mountainous landscape, topography and land cover types have major role in determining soil quality. DTM-based soil–landscape units’ delineation can be helpful to study soil quality variability and can be used to generate soil map for the hilly and mountainous watershed. The significance of this study lies in its potential to make substantial contributions to land use planning, sustainable land management and environmental conservation planning in the challenging and ecologically fragile and sensitive Himalayan region.

Soil erosion is expected to worsen in the future as a result of climate change, growing population demands, improper land use, and excessive exploitation of natural resources in India. Due to the growing population and changes in land use, it has become increasingly crucial to map and quantitatively assess soil for the purpose of sustainable agricultural usage and planning conservation efforts. The problem of soil erosion is mainly on steeper slopes with intense rainfall in parts of Western Ghats. The 20.17% of geographical area have been converted into wasteland due to soil erosion. The Revised Universal Soil Loss Equation (RUSLE) is a highly prevalent and effective technique utilized for estimating soil loss in order to facilitate the planning of erosion control measures. Despite the fact that RUSLE is accurately estimate sediment yields from gully erosion, it is an effective tool in estimating sheet and rill erosions losses from diverse land uses like agricultural to construction sites. The current study is mainly about combining the RUSLE model with GIS (Geographic Information System) to find out how much soil is being lost, particularly in Noyyal and Sanganur watersheds which is located in Coimbatore district of Tamil Nadu, India. This analysis is based on the soil order, with a significant proportion of alfisols and inceptisols being considered. The obtained outcome is contrasted with the established soil loss tolerance threshold, leading to the identification of the areas with the highest susceptibility to erosion. Within the narrower and more inclined section of the watershed, yearly soil loss scales from 0 to 5455 tonnes/ha/year, with an average annual loss of soil of 2.44 tonnes/ha. The severe soil erosion of 100 to 5455 tonnes/ha/year is found along the steep and greater slope length. The generated soil map was classified into six categories: very slight, slight, moderate, high, severe, and very severe. These classifications, respectively, occupied 6.23%, 14.88%, 10.56%, 15.70%, 7.73%, and 6.63% of the basin area. Based on the results of cross-validation, the estimated result of the present study was found to be very high compared to past studies conducted 0 to 368.12 tonnes/ha/year especially in very severe erosion zones. But very slight to severe erosion zones nearly matched with same level of soil loss. To protect the soil in the study area from erosion, more specific actions should be taken. These include micro-catchment, broad bed furrows, up-and-down farming, soil amendment with coconut coir pith composition, streambank stabilization with vegetation, and micro-water harvesting with abandoned well recharge. These actions should be carried out over time to make sure to work.

Winter wheat (Triticum aestivum L.) is one of the most important cereal crops, supplying essential food for the world population. Because the United States is a major producer and exporter of wheat to the world market, accurate and timely forecasting of wheat yield in the United States (U.S.) is fundamental to national crop management as well as global food security. Previous studies mainly have focused on developing empirical models using only satellite remote sensing images, while other yield determinants have not yet been adequately explored. In addition, these models are based on traditional statistical regression algorithms, while more advanced machine learning approaches have not been explored. This study used advanced machine learning algorithms to establish within-season yield prediction models for winter wheat using multi-source data to address these issues. Specifically, yield driving factors were extracted from four different data sources, including satellite images, climate data, soil maps, and historical yield records. Subsequently, two linear regression methods, including ordinary least square (OLS) and least absolute shrinkage and selection operator (LASSO), and four well-known machine learning methods, including support vector machine (SVM), random forest (RF), Adaptive Boosting (AdaBoost), and deep neural network (DNN), were applied and compared for estimating the county-level winter wheat yield in the Conterminous United States (CONUS) within the growing season. Our models were trained on data from 2008 to 2016 and evaluated on data from 2017 and 2018, with the results demonstrating that the machine learning approaches performed better than the linear regression models, with the best performance being achieved using the AdaBoost model (R2 = 0.86, RMSE = 0.51 t/ha, MAE = 0.39 t/ha). Additionally, the results showed that combining data from multiple sources outperformed single source satellite data, with the highest accuracy being obtained when the four data sources were all considered in the model development. Finally, the prediction accuracy was also evaluated against timeliness within the growing season, with reliable predictions (R2 > 0.84) being able to be achieved 2.5 months before the harvest when the multi-source data were combined.

Erosion of soil by water coupled with human activities is considered as one of the most serious agents of land degradation, posing severe threat to agricultural productivity, soil health, water quality, and ecological setup. The assessment of soil erosion and recognition of problematic watersheds are pre-requisite for management of erosion hazards. In the present study, Revised Universal Soil Loss Equation (RUSLE) integrated with remote sensing (RS) and geographic information system (GIS) has been used to assess the soil erosion in lower Sutlej River basin of Punjab, India, and prioritize the watersheds for implementation of land and water conservation measures. The total basin area was about 8577 km 2 which was divided into 14 sub-watersheds with the area ranging from 357.8 to 1354 km 2 . The data on rainfall (IMD gridded data), soil characteristics (FAO soil map), topography (ALOS PALSAR DEM) and land use (ESRI land use and land cover map) were prepared in the form of raster layers and overlaid together to determine the average annual soil loss. The results revealed that the average annual soil loss varied from 1.26 to 25 t ha −1 , whereas total soil loss was estimated to be 2,441,639 tonnes. The spatial distribution map of soil erosion showed that about 94.4% and 4.7% of the total area suffered from very slight erosion (0–5 t ha −1  year −1 ) and slight erosion (5–10 t ha −1  year −1 ), respectively, whereas 0.11% (9.38 km 2 ) experienced very severe soil loss (> 25 t ha −1  year −1 ). Based on estimated average annual soil loss of sub-watersheds, WS8 was assigned the highest priority for implementation of soil and water conservation measures (323.5 t ha −1  year −1 ), followed by WS9 (303.8 t ha −1  year −1 ), whereas WS2 was given last priority owing to its lowest value of soil loss (122.02 t ha −1  year −1 ). The present study urges that conservation strategies should be carried out in accordance with the priority ranking of diverse watersheds. These findings can certainly be used to implement soil conservation plans and management practices in order to diminish soil loss in the river basin.

Like the oceans, which store heat and create a “memory” in the climate system, the land also accumulates water, which also contributes to climate persistence. One of the considerable sources of uncertainty in regional climate models, which are crucial climate impact and adaptation support tools, is related to soil texture datasets and its soil parameters. Soil properties, defined by parameters in soil datasets, influence surface water and energy cycles and hence play a role in land-atmosphere exchanges. In this study, the main goal was to inspect uncertainty of the simulated mean and extreme climate to changes in prescribed soil texture datasets. We performed climate simulations over Europe with a particular focus on the Pannonian Basin during the summer season with a fully coupled regional climate model EBU-POM using two different soil maps: the STATSGO/FAO global hybrid map and the Zobler soil texture map generalized from the FAO Soil Map of the World, which has a lower spatial resolution. The simulations showed that regions with lower latent heat (corresponding to a lower evaporative fraction) coincide with areas that have a higher 2-m temperature (above + 0.4 °C) and drier soils (with a soil moisture content of less than − 60 mm). Also, differences in soil moisture content, primarily driven by changes in soil texture, largely coincide with differences in parameters such as the wilting point and soil water diffusivity which highlight the importance of these parameters in shaping surface fluxes. Furthermore, these experiments illustrate the important role of soil parameters in the dynamics of the summer climate, as they affect the coupling strength and consequently influence climate and its extremes. Results suggest that the choice of soil parameters/soil texture datasets has considerable consequences, especially on climate extremes, as biases and coupling strength can be more pronounced.

Soil plays a critical role in nutrient availability, microbial activity, and fertility in agriculture. However, the effects of agroclimatic conditions on soil pH are not well understood, particularly in the Horro Guduru Zone of Ethiopia. This study aimed to investigate the soil pH under extremely wet and dry conditions across 3 shared socioeconomic pathway (SSP) scenarios: SSP1-2.6, SSP2-4.5, and SSP5-8.5. Baseline agroclimatic data (1981–2010) and future projections (2041–2070) were obtained from the European Commission Climate Change Services. Soil pH data at a 250 m resolution were extracted from the FAO-UNESCO global soil map. Missing values, multicollinearity, and outliers were addressed before modeling. Predictive models, including neural networks, generalized regression, and bootstrap forests, were validated, with the generalized regression model showing the best performance. The results indicate that soil pH decreases under consecutive dry‒wet conditions and increases with increasing maximum day temperatures across all scenarios. Soil pH is significantly influenced by the number of consecutive dry days, consecutive wet days, and maximum day temperature. The SSP1-2.6 and SSP2-4.5 scenarios resulted in improved pH levels, whereas SSP5-8.5 led to a decrease in soil pH, averaging 5.79 and decreasing to 5.54. These findings suggest that under SSP5-8.5, soil health and farming productivity may be compromised. This study emphasizes the need to adjust soil management practices based on prevailing climatic conditions to ensure soil health and agricultural sustainability.