•First comprehensive application of 15 data mining models to soil erosion.•Game theory was applied to assess the interpretability of the DM models.•BGAM is the most accurate model.•DEM derived ...factors are the most important controls.•Game theory is a valuable technique for assessing the interpretability of predictive models.
This study undertook a comprehensive application of 15 data mining (DM) models, most of which have, thus far, not been commonly used in environmental sciences, to predict land susceptibility to water erosion hazard in the Kahorestan catchment, southern Iran. The DM models were BGLM, BGAM, Cforest, CITree, GAMS, LRSS, NCPQR, PLS, PLSGLM, QR, RLM, SGB, SVM, BCART and BTR. We identified 18 factors usually considered as key controls for water erosion, comprising 10 factors extracted from a digital elevation model (DEM), three indices extracted from Landsat 8 images, a sediment connectivity index (SCI) and three other intrinsic factors. Three indicators consisting of MAE, MBE, RMSE, and a Taylor diagram were applied to assess model performance and accuracy. Game theory was applied to assess the interpretability of the DM models for predicting water erosion hazard. Among the 15 predictive models, BGAM and PLS respectively returned the best and worst performance in predicting water erosion hazard in the study area. The most accurate model, BGAM predicted that 22%, 8.2%, 9.4% and 60.4% of the total area should be classified as low, moderate, high and very high susceptibility to soil erosion by water, respectively. Based on BGAM and game theory, the factors extracted from the DEM (e.g., DEM, TWI, Slope, TST, TRI, and SPI) were considered the most important ones controlling the predicted severity of soil erosion by water. We conclude that overall, game theory is a valuable technique for assessing the interpretability of predictive models because this theory through SHAP (Shapley additive explanations) and PFIM (permutation feature importance measure) addresses the important concerns regarding the interpretability of more complex DM models.
The open access book aims to show the readers novel, relevant and reproducible power of synergistic collaborations between European research groups and stakeholders with the objective to synthesize ...the existing knowledge and expertise about fire management and hazard and defining a concerted research agenda that promotes an integrated approach to create fire-resilient landscapes, taking into account biological, biochemical and physical, but also socio-economic, historical, geographical, sociological, perception and policy constraints. This is an urgent societal need due to the expected further intensification and geographical spreading of wildfire regimes under Global Change. Fire has been part of the Earth's System for the last 400 million years, and humans are the sole species that controls and manages fire. We have used fire for over a million years, both, as hunter-gatherers managing the landscape with fire and as farmers using fire as a low-cost, efficient and ecological tool for clearing and maintaining the productivity of the land. Fire has been highlighted as the most influential element in the development of human societies. The increase in prolonged dry and hot periods observed in many regions of the world is exacerbating the risk of fire. The causes of increased fire risk are not only linked to climate change but are also a consequence of economic and social changes and political decisions. Over the past few decades, many countries’ rural areas have seen significant depopulation and a reduction in land management as residents moved to cities or even other countries in search of work. The resulting rural depopulation has led to revegetation of the abandoned agricultural land, which favors fire spread. The enhanced risk of fires is moving beyond the capacity of even the best-funded wildland firefighting teams and therefore calls for the development of new approaches to fire management that are key nowadays at different scales. Instead of focusing primarily on increasing firefighting capabilities, a more effective approach is needed that focuses on long-term fire prevention through vegetation management by reducing fuel load or managing fuel type and fuel continuity at a landscape level. FIRElinks (COST Action CA18135) is developing the EU-spanning network of scientists and practitioners involved in forest fire research and land management with backgrounds such as fire dynamics, fire risk management, fire effects on vegetation, fauna, soil and water and socio-economic, historical, geographical, political perception and land management approaches. Among the different Working Groups, number 5 is aimed to connect communities from different scientific and geographic backgrounds, allowing the discussion of different experiences and the emergence of new approaches to fire research, human management, regional issues and socio-economic aspects.
Soil salinisation is a pervasive form of land degradation posing a significant threat to the global environment. Saline soil, covering roughly 10% of the total land area, represents a crucial reserve ...of land resources. The use of super absorbent polymer (SAP) impacts capillary water movement through the soil because of its exceptional water absorption and retention capabilities. SAP is expected to influence the intricate water‐salt migration processes and their redistribution within soil. This study employed soil column experiments to investigate the impacts of varying SAP dosages (A), heights (B) and thicknesses (C) on soil water and salt transport in the Tianjin Binhai New Area, China. The main findings showed that: (1) average capillary water rise rate decreased with SAP dosage increase. The groundwater recharge trend in time was like that of capillary water rise height; (2) SAP usage increased water and salt content on the application layer and reduced surface soil salt accumulation; (3) the best SAP combination for application was 1.1% SAP at 17–18 cm from the groundwater level. This study provides basic effective SAP application strategies for preventing soil salinisation.
Water quality is a big concern for the humankind as it is the most important natural resource. However, the non-controlled growth of rural and urban areas in rapidly developed countries such as India ...is affecting water quality. In this research, we pretend to assess and demonstrate the heavy-metal status of three different water bodies of Indus, Beas and Sutlej Rivers and Harike Wetland. Data on water quality from 2013 to 2017 were analyzed through multivariate statistic techniques (cluster analysis - CA - and principal component analysis - PCA) and compared among them using public water pollution indexes. The results of CA and PCA showed that Sutlej River and Harike Wetland are included in the same group, whereas Beas River formed a separate one. This may be due to the high content of Pb, Cu, and Zn in these water bodies as compared with Beas River. The Pb content of all the water bodies exceeded the limit for EPR, BIS and WHO guidelines for drinking water. The heavy-metal pollution index was also applied to the contents of different heavy metals to find which water body is more polluted, and from their results, it was found that Harike Wetland and Sutlej River are critically polluted with heavy metals.
Connecting the public with soil to improve human health Brevik, Eric C.; Steffan, Joshua J.; Rodrigo‐Comino, Jesús ...
European journal of soil science,
July 2019, 2019-07-00, 20190701, Letnik:
70, Številka:
4
Journal Article
Recenzirano
Odprti dostop
Despite the definite links between soil and human health, it is likely that most people do not think about soil when considering human health. There is a disconnect between most people in our modern ...society and soil, and when people notice soil it is often in a negative context. People care for things that matter to them, and creating a more positive public image of soil could improve human health by leading to better treatment and understanding of the soil resource. There are a number of concepts that may be able to connect people to the soil, including terroir, soil health and soil security. While terroir originally established a connection between those who appreciate wine and the soils that produce those wines, the concept has been expanded to many additional products. It might be possible to provide a terroir link to human health benefits if they can be shown to be characteristic of a given soil environment. The concept of soil health has caught on with many farmers, policymakers, scientists and the general public, thus providing another possible approach to improve peoples’ connection with soil. Soil security is a recent concept that has been advanced as a way to take advantage of the connection that concepts such as energy, food and water security have made with policymakers. Therefore, we advocate a concerted effort to investigate terroir, soil health and soil security as concepts to improve overall human health. Soil health and soil security might have the most promise, and some social marketing campaigns that include soil health are ongoing.
Highlights
Soil is important to human health.
A disconnect exists between the urban population and soil.
Education about soil can rebuild these connections.
Concepts such as terroir, soil health or soil security might help make connections.
Natural hazards are diverse and uneven in time and space, therefore, understanding its complexity is key to save human lives and conserve natural ecosystems. Reducing the outputs obtained after each ...modelling analysis is key to present the results for stakeholders, land managers and policymakers. So, the main goal of this survey was to present a method to synthesize three natural hazards in one multi-hazard map and its evaluation for hazard management and land use planning. To test this methodology, we took as study area the Gorganrood Watershed, located in the Golestan Province (Iran). First, an inventory map of three different types of hazards including flood, landslides, and gullies was prepared using field surveys and different official reports. To generate the susceptibility maps, a total of 17 geo-environmental factors were selected as predictors using the MaxEnt (Maximum Entropy) machine learning technique. The accuracy of the predictive models was evaluated by drawing receiver operating characteristic-ROC curves and calculating the area under the ROC curve-AUCROC. The MaxEnt model not only implemented superbly in the degree of fitting, but also obtained significant results in predictive performance. Variables importance of the three studied types of hazards showed that river density, distance from streams, and elevation were the most important factors for flood, respectively. Lithological units, elevation, and annual mean rainfall were relevant for detecting landslides. On the other hand, annual mean rainfall, elevation, and lithological units were used for gully erosion mapping in this study area. Finally, by combining the flood, landslides, and gully erosion susceptibility maps, an integrated multi-hazard map was created. The results demonstrated that 60% of the area is subjected to hazards, reaching a proportion of landslides up to 21.2% in the whole territory. We conclude that using this type of multi-hazard map may be a useful tool for local administrators to identify areas susceptible to hazards at large scales as we demonstrated in this research.
The drastic growth of population in highly industrialized urban areas, as well as fossil fuel use, is increasing levels of airborne pollutants and enhancing acid rain. In rapidly developing countries ...such as Iran, the occurrence of acid rain has also increased. Acid rain is a driving factor of erosion due to the destructive effects on biota and aggregate stability; however, little is known about its impact on specific rates of erosion at the pedon scale. Thus, the present study aimed to investigate the effect of acid rain at pH levels of 5.25, 4.25, and 3.75 for rainfall intensities of 40, 60, and 80 mm h−1 on initial soil erosion processes under dry and saturated soil conditions using rainfall simulations. The results were compared using a two‐way ANOVA and Duncan tests and showed that initial soil erosion rates with acidic rain and non‐acidic rain under dry soil conditions were significantly different. The highest levels of soil particle loss due to splash effects in all rainfall intensities were observed with the most acidic rain (pH = 3.75), reaching maximum values of 16 g m−2 min−1. The lowest levels of particle losses were observed in the control plot where non‐acidic rain was used, with values ranging from 3.8 to 8.1 g m−2 min−1. Similarly, under saturated soil conditions, the lowest level of soil particle loss was observed in the control plot, and the highest peaks of soil loss were observed for the most acidic rains (pH = 3.75 and pH = 4.25), reaching maximum average values of 40 g m−2 min−1. However, for saturated soils with acidic water but with non‐acidic rain, the highest soil particle loss was observed for the control plot for all the rainfall intensities. In conclusion, acidic rain has a negative impact on soils, which can be more intense with a concomitant increase in rainfall intensity. Rapid solutions, therefore, need to be found to reduce the emission of pollutants into the air, otherwise, rainfall erosivity may drastically increase.