Terrain Attributes Research Articles

Predicting Gross Primary Productivity under Future Climate Change for the Tibetan Plateau Based on Convolutional Neural Networks

Gross primary productivity (GPP) is vital for ecosystems and the global carbon cycle, serving as a sensitive indicator of ecosystems’ responses to climate change. However, the impact of future climate changes on GPP in the Tibetan Plateau, an ecologically important and climatically sensitive region, remains underexplored. This study aimed to develop a data-driven approach to predict the seasonal and annual variations in GPP in the Tibetan Plateau up to the year 2100 under changing climatic conditions. A convolutional neural network (CNN) was employed to investigate the relationships between GPP and various environmental factors, including climate variables, CO2 concentrations, and terrain attributes. This study analyzed the projected seasonal and annual GPP from the Coupled Model Intercomparison Project Phase 6 (CMIP6) under four future scenarios: SSP1–2.6, SSP2–4.5, SSP3–7.0, and SSP5–8.5. The results suggest that the annual GPP is expected to significantly increase throughout the 21st century under all future climate scenarios. By 2100, the annual GPP is projected to reach 1011.98 Tg C, 1032.67 Tg C, 1044.35 Tg C, and 1055.50 Tg C under the four scenarios, representing changes of 0.36%, 4.02%, 5.55%, and 5.67% relative to 2021. A seasonal analysis indicates that the GPP in spring and autumn shows more pronounced growth under the SSP3–7.0 and SSP5–8.5 scenarios due to the extended growing season. Furthermore, the study identified an elevation band between 3000 and 4500 m that is particularly sensitive to climate change in terms of the GPP response. Significant GPP increases would occur in the east of the Tibetan Plateau, including the Qilian Mountains and the upper reaches of the Yellow and Yangtze Rivers. These findings highlight the pivotal role of climate change in driving future GPP dynamics in this region. These insights not only bridge existing knowledge gaps regarding the impact of future climate change on the GPP of the Tibetan Plateau over the coming decades but also provide valuable guidance for the formulation of climate adaptation strategies aimed at ecological conservation and carbon management.

Proposal of a facet-to-facet multiple flow direction algorithm based on geometrical and mathematical analysis of physical dispersion over triangle facet

Flow direction algorithms have been widely used to extract crucial terrain attributes of great hydrological and geomorphological significance. However, essential distinctions between the empirically-designed strategies of typical algorithms and the natural rules of physical dispersions bring various problems (e.g. parallel channel, artificial dispersion), leading to the low size and extent precisions of estimated results. In this work, geometrical and mathematical analysis is conducted on the inherent characteristics of physical dispersions along slope lines on local terrains. On each 3 × 3 window of digital elevation model (DEM), center pixel is divided into eight non-overlapping sub-facets. Necessary and sufficient (NS) conditions of size relationships between the elevations of adjacent pixels are summarized to directly identify the receiving facets of a sub-facet. Then, strict mathematical relations are derived between slope direction of a sub-facet and flow proportions allocated to receiving facets. A strategy is designed to re-adjust receiving facets and flow proportions for the boundary flow of adjacent facets. Lastly, a multiple-flow-direction algorithm called TFGA is proposed with the NS condition of size relationships, mathematical relation of slope direction with flow proportion, and adjustment strategy of boundary flow. Case studies are conducted for investigating the total contributing areas (TCA) and specific contributing areas (SCA) estimated by TFGA. Results reveal all-side superiorities of TFGA to typical algorithms in spatial patterns, error indicators and statistic characteristics of estimated TCAs and SCAs. Particularly, TFGA improves size precision of estimated results by approximately one order of magnitude. In a conclusion, we highly recommend TFGA for digital elevation analysis.

Assessing soil fungal diversity under different sampling schemes in conjunction with remote sensing technologies in a subtropical forest

Fungi, serving as real-time bioindicators to environmental changes and stressors, are crucial for effective forest conservation and management practices under ongoing global change. However, the large-scale assessment of soil fungi still encounters challenges in striking a balance between the extensive sampling costs and the limited accuracy of minimal sampling. In this study, we analyzed 1,606 soil samples collected from 625 quadrats (20 m × 20 m) within a 25-ha subtropical forest dynamic plot in East China. Our primary objective was to explore the impact of different sampling schemes, in conjunction with remote sensing (RS) technologies, on the interpolation of soil fungal diversity using Ordinary Kriging (OK) and Co-kriging (CoK) models. Our findings suggested that a sampling scheme including points at 0 m (the base points) and 8 m within each quadrat, totaling to 26 points/ha, would be a sufficient scheme. This scheme with OK model yielded comparable results to those of more intensive schemes (at 0, 2, 5 and 8 m), but required the fewest sampling points. Upon incorporating each RS variable separately into the CoK models, including two vegetation indices (normalized difference vegetation index and transformed chlorophyll absorption ratio index 2), three terrain attributes (Elevation, Aspect and Slope), and the synthesis of these RS variables, the accuracy of the predicted results was further improved for each sampling scheme. By leveraging high-precision soil DNA sequencing in conjunction with cost-effective RS technologies, this study proposes a rapid and affordable approach for monitoring soil fungal diversity on a large scale. This will facilitate data collection for understanding responses of forest soil fungi to ongoing global change.

Evaluating spectral properties of invasive plant species in Kentucky recreation areas

ABSTRACT This study examines the spectral characteristics of two invasive plant species, Amur honeysuckle (Lonicera maackii) and Callery ‘Bradford’ pear (Pyrus calleryana Decne), in central Kentucky’s recreational areas. Using a combination of spectrometer, satellite (National Agriculture Imagery Program (NAIP)) and unmanned aerial vehicle (UAV) data, this study investigated the correlation between leaf locations and normalized difference vegetation index (NDVI), as well as the impact of terrain features on vegetation indices. Significant variations in NDVI and normalized difference red-edge (NDRE) index values across study areas and leaf positions were observed. Terrain attributes, particularly slope and aspect direction, significantly influenced vegetative indices in one study site. Weak to moderate correlations were found between the spectrometer and UAV-derived NDVI and NDRE values. Additionally, the study highlighted the feasibility of upscaling UAV data for NAIP imagery comparison, reaffirming the superior accuracy of UAV imagery in assessing vegetation health. This integration of remote sensing techniques offers valuable insights into the spectral characteristics of invasive plants, essential for their effective mapping and management.

Predicting Seasonal Deformation Using InSAR and Machine Learning in the Permafrost Regions of the Yangtze River Source Region

AbstractQuantifying seasonal deformation is essential for accurately determining the thickness of the active layer and the distribution of water content within it, providing insights into the freeze‐thaw dynamics of permafrost environments and their sensitivity to climate change. Due to the limited hydraulic conductivity of the underlying permafrost, the freeze‐thaw processes are largely confined to the active layer, allowing for predictable seasonal deformations. This study employed Independent Component Analysis to isolate large‐scale seasonal deformation from Interferometric Synthetic Aperture Radar (InSAR) measurements taken from 2016 to 2020 in the Yangtze River Source Region (YRSR) of the Qinghai‐Tibet Plateau (QTP), covering 18,500 km2. We developed dedicated machine learning (ML) models that integrate these InSAR‐derived measurements with various environmental proxies. By applying these models to the YRSR, we generated a comprehensive, full‐coverage deformation map for permafrost terrains, achieving an R2 value of 0.91 and an Root Mean Squared Error of approximately 0.5 cm, thus confirming the model's strong predictability of seasonal deformation in permafrost regions. Deformation magnitude varied from less than 1 cm to over 10 cm. Our analysis suggests that terrain attributes, influenced by climate and soil conditions, are the primary factors driving these deformations. This research provides valuable insights into quantifying permafrost‐related seasonal deformation across expansive and rural landscapes. It also aids in assessing subsurface hydrological processes and the resilience and vulnerability of permafrost. The developed ML algorithm, with access to precise environmental data, is capable of forecasting seasonal deformations across the entire QTP and potentially throughout the Arctic.

Exploiting Soil and Remote Sensing Data Archives for 3D Mapping of Multiple Soil Properties at the Swiss National Scale

Soils play a central role in ecosystem functioning, and thus, mapped soil property information is indispensable to supporting sustainable land management. Digital Soil Mapping (DSM) provides a framework to spatially estimate soil properties. However, broad-scale DSM remains challenging because of non-purposively sampled soil data, large data volumes for processing extensive soil covariates, and high model complexities due to spatially varying soil–landscape relationships. This study presents a three-dimensional DSM framework for Switzerland, targeting the soil properties of clay content (Clay), organic carbon content (SOC), pH value (pH), and potential cation exchange capacity (CECpot). The DSM approach is based on machine learning and a comprehensive exploitation of soil and remote sensing data archives. Quantile Regression Forest was applied to link the soil sample data from a national soil data base with covariates derived from a LiDAR-based elevation model, from climate raster data, and from multispectral raster time series based on satellite imagery. The covariate set comprises spatially multiscale terrain attributes, climate patterns and their temporal variation, temporarily multiscale land use features, and spectral bare soil signatures. Soil data and predictions were evaluated with respect to different landcovers and depth intervals. All reference soil data sets were found to be spatially clustered towards croplands, showing an increasing sample density from lower to upper depth intervals. According to the R2 value derived from independent data, the overall model accuracy amounts to 0.69 for Clay, 0.64 for SOC, 0.76 for pH, and 0.72 for CECpot. Reduced model accuracies were found to be accompanied by soil data sets showing limited sample sizes (e.g., CECpot), uneven statistical distributions (e.g., SOC), and low spatial sample densities (e.g., woodland subsoils). Multiscale terrain covariates were highly influential for all models; climate covariates were particularly important for the Clay model; multiscale land use covariates showed enhanced importance for modeling pH; and bare soil reflectance was a major driver in the SOC and CECpot models.

МЕТОДИКА ПОДДЕРЖКИ ПРИНЯТИЯ РЕШЕНИЙ ПО ВЫБОРУ МЕСТОПОЛОЖЕНИЯ ЭЛЕМЕНТОВ ГРУППИРОВКИ СИЛ И СРЕДСТВ ПРИ ЛИКВИДАЦИИ ЧРЕЗВЫЧАЙНЫХ СИТУАЦИЙ

For this period of time, the EMERCOM of Russia system has developed and uses mainly «manual» and partially automated calculation methods when planning the location of elements of the emergency response grouping. The main disadvantages of the known methods are the high labor and time costs, the need for highly qualified performers, as well as the significant importance of the subjectivity factor in the results obtained. When implementing the planning process, these factors negatively affect the quality of calculations. Automation of calculations using a model for estimating the properties of terrain on a digital map in the proposed formats is considered. The approbation of the methodology proposed in the article for solving the problems of choosing the location of elements of the grouping of forces and means in the aftermath of an emergency situation shows that the use of a digital terrain map really allows you to improve the quality of decisions.

Importance of Terrain and Climate for Predicting Soil Organic Carbon Is Highly Variable across Local to Continental Scales.

Soil organic carbon (SOC) plays a vital role in global carbon cycling and sequestration, underpinning the need for a comprehensive understanding of its distribution and controls. This study explores the importance of various covariates on SOC spatial distribution at both local (up to 1.25 km) and continental (USA) scales using a deep learning approach. Our findings highlight the significant role of terrain attributes in predicting SOC concentration distribution with terrain, contributing approximately one-third of the overall prediction at the local scale. At the continental scale, climate is only 1.2 times more important than terrain in predicting SOC distribution, whereas at the local scale, the structural pattern of terrain is 14 and 2 times more important than climate and vegetation, respectively. We underscore that terrain attributes, while being integral to the SOC distribution at all scales, are stronger predictors at the local scale with explicit spatial arrangement information. While this observational study does not assess causal mechanisms, our analysis nonetheless presents a nuanced perspective about SOC spatial distribution, which suggests disparate predictors of SOC at local and continental scales. The insights gained from this study have implications for improved SOC mapping, decision support tools, and land management strategies, aiding in the development of effective carbon sequestration initiatives and enhancing climate mitigation efforts.

Soil textural class modeling using digital soil mapping approaches: Effect of resampling strategies on imbalanced dataset predictions

In a digital soil mapping (DSM) context, machine learning (ML) algorithms are widely used to model soil textural classes (STCs). However, in the real world most soil class datasets exhibit imbalanced distributions. This poses a challenge as ML algorithms are designed to handle balanced classes, leading to a bias towards the majority classes while often overlooking the minority classes. Furthermore, within the DSM framework, two strategies can be employed to model STCs: direct and indirect approaches. In the direct approach, STCs are directly inputted into the model for prediction. In contrast, the indirect approach involves introducing soil texture fractions (i.e., clay, silt, sand) as initial inputs, then STCs are obtained from the outputs. Limited research has been conducted on the impact of data balancing on STC predictions, and there is a lack of comparative analysis between direct and indirect approaches in this context. Therefore, this study aimed to evaluate the efficacy of a resampling technique (SMOTE: synthetic minority oversampling technique) in handling an imbalanced soil texture dataset collected from the Kuhdasht region in western Iran. Additionally, the study sought to compare the performance of direct and indirect modeling approaches. Environmental covariates derived from Landsat 8 and Sentinel 2 images along with a digital elevation model (DEM) were used as input variables to a random forest (RF) model to model STCs and soil texture fractions. The results revealed that terrain attributes and Euclidean distances played a more significant role in modeling both balanced and imbalanced datasets compared to remotely sensed data. Kappa indices for balanced and imbalanced datasets, as well as for the indirect approach were found to be 89%, 68% and 38% respectively. In the same way, the overall accuracies were 91%, 79% and 68%, respectively. Among the imbalanced classes, clay loam and loam which accounted for the majority of observations showed the highest recall values, followed by sandy clay loam, sandy loam and silty clay loam. When employing the indirect approach, the RF model failed to capture the minority classes in terms of validation statistics. Additionally, modeling with the imbalanced dataset resulted in the exclusion of three minority STCs from the final map. Overall, this study showed the importance of balancing STCs prior to modeling to achieve more accurate estimates of STCs, as well as the superiority of employing the direct approach (using balanced data sets) over the indirect approach.

Detection of karst depression in Brazil comparing different semantic and instance segmentations and global digital elevation models

This research assessed the efficacy of deep segmentation in identifying and measuring natural karst depressions in the Bambuí Group's carbonate rocks in Western Bahia, Brazil. The investigation used five Global Digital Elevation Models (DEMs) with 30-m resolution: Advanced Spaceborne Thermal Emission and Reflection Radiometer - Global Digital Elevation Model version 3 (ASTER-GDEM v3), Advanced Land Observing Satellite World 3D – 30 m version 3.2 (AW3D30 v3.2), Copernicus 30 m global DEM (GLO-30), NASA Digital Elevation Model version 1 (NASADEM v1), and Shuttle Radar Topography Mission version 3 (SRTM v3). The karst feature detection analysis compared five semantic segmentation architectures: Feature Pyramid Networks (FPN), LinkNet, UNet, UNet++, DVL3+, using an EfficientNet-B7 backbone, one instance segmentation model (Mask-RCNN), and a semantic-to-instance conversion method. This comparison considers different datasets, including one, two, or eleven variables (DEM, DEM-based sink depth, and nine terrain attributes). Besides, we performed a combinatorial analysis of the DEMs to evaluate the improvement in karst feature detection. The methodology involved the generation of geomorphometric attributes, sample labeling from Sentinel-2 and Operational Land Imager-Landsat 8 datasets, training-validation-testing steps with 128 × 128 samples, reconstruction of large images for semantic and instance segmentation, and accuracy analysis. The findings revealed that GLO-30 and AW3D30 data were the most accurate, while ASTER GDEM performed poorly in both segmentation forms. Among the semantic models, FPN showed the highest accuracy. The 11-variable models preferentially outperformed those with fewer in both types of segmentation. The approach of semantic-to-instance conversion with Geographic Information System tools favored individualizing karst depressions and obtaining efficient quantification, consisting of an easy alternative to achieve instance segmentation. Reconstruction of large remote sensing images through sliding windows considering the specifics of instance and semantic segmentation demonstrated that smaller stride enhances object coverage and reduces the risk of losing crucial information, effectively improving the predictions. The combinatorial analysis for semantic and instance segmentation indicates that models incorporating more DEMs (4- and 5-DEM models) and variables achieve generally higher accuracy. The best result in semantic segmentation was combining the five DEM datasets using 11 variables, reaching an F-score of 85.06 and IoU of 74.00. In instance segmentation, the best result for the bounding box was the model that integrates AW3D30, GLO-30, NASADEM, and SRTM with eleven variables reaching Average Precision (AP) of 45.64, AP50 of 88.40 and AP75 of 39.38, while the best result for the segmentation mask was the model that integrates the five models with eleven variables with AP of 42.61, AP50 of 86.79 and AP75 of 35.43. These results demonstrate that integrating a wide range of DEM data, even the lowest performing ones, improves model generalization and accuracy in segmentation, leveraging strengths and mitigating individual weaknesses. Future work could explore high-resolution DEMs and the integration of various deep-learning methods.

Suitability of satellite-based rainfall products for estimating rainfall erosivity in areas with contrasted climate and terrain properties: Example of west-central Morocco

Suitability of satellite-based rainfall products for estimating rainfall erosivity in areas with contrasted climate and terrain properties: Example of west-central Morocco

Viability leads to the emergence of gait transitions in learning agile quadrupedal locomotion on challenging terrains

Quadruped animals are capable of seamless transitions between different gaits. While energy efficiency appears to be one of the reasons for changing gaits, other determinant factors likely play a role too, including terrain properties. In this article, we propose that viability, i.e., the avoidance of falls, represents an important criterion for gait transitions. We investigate the emergence of gait transitions through the interaction between supraspinal drive (brain), the central pattern generator in the spinal cord, the body, and exteroceptive sensing by leveraging deep reinforcement learning and robotics tools. Consistent with quadruped animal data, we show that the walk-trot gait transition for quadruped robots on flat terrain improves both viability and energy efficiency. Furthermore, we investigate the effects of discrete terrain (i.e., crossing successive gaps) on imposing gait transitions, and find the emergence of trot-pronk transitions to avoid non-viable states. Viability is the only improved factor after gait transitions on both flat and discrete gap terrains, suggesting that viability could be a primary and universal objective of gait transitions, while other criteria are secondary objectives and/or a consequence of viability. Moreover, our experiments demonstrate state-of-the-art quadruped robot agility in challenging scenarios.

Mapping queen snapper (Etelis oculatus) suitable habitat in Puerto Rico using ensemble species distribution modeling.

Queen snapper (Etelis oculatus) is of interest from an ecological and management perspective as it is the second most landed finfish species (by total pounds) as determined by Puerto Rico commercial landings (2010-2019). As fishing activities progressively expand into deeper waters, it is critical to gather data on deep-sea fish populations to identify essential fish habitats (EFH). In the U.S. Caribbean, the critically data-deficient nature of this species has made this challenging. We investigated the use of ensemble species distribution modeling (ESDM) to predict queen snapper distribution along the coast of Puerto Rico. Using occurrence data and terrain attributes derived from bathymetric datasets at different resolutions, we developed species distribution models unique to each sampling region (west, northeast, and southeast Puerto Rico) using seven different algorithms. Then, we developed ESDM models to analyze fish distribution using the highest-performing algorithms for each region. Model performance was evaluated for each ensemble model, with all depicting 'excellent' predictive capability (AUC > 0.8). Additionally, all ensemble models depicted 'substantial agreement' (Kappa > 0.7). We then used the models in combination with existing knowledge of the species' range to produce binary maps of potential queen snapper distributions. Variable importance differed across spatial resolutions of 30 m (west region) and 8 m (northeast and southeast region); however, bathymetry was consistently one of the best predictors of queen snapper suitable habitat. Positive detections showed strong regional patterns localized around large bathymetric features, such as seamounts and ridges. Despite the data-deficient condition of queen snapper population dynamics, these models will help facilitate the analysis of their spatial distribution and habitat preferences at different spatial scales. Our results therefore provide a first step in designing long-term monitoring programs targeting queen snapper, and determining EFH and the general distribution of this species in Puerto Rico.

Digital Mapping of Soil Particle Size Fractions in the Loess Plateau, China, Using Environmental Variables and Multivariate Random Forest

Soil particle size fractions (PSFs) are important properties for understanding the physical and chemical processes in soil systems. Knowledge about the distribution of soil PSFs is critical for sustainable soil management. Although log-ratio transformations have been widely applied to soil PSFs prediction, the statistical distribution of original data and the transformed data given by log-ratio transformations is different, resulting in biased estimates of soil PSFs. Therefore, multivariate random forest (MRF) was utilized for the simultaneous prediction of soil PSFs, as it is able to capture dependencies and internal relations among the three components. Specifically, 243 soil samples collected across the Loess Plateau were used. Meanwhile, Landsat data, terrain attributes, and climatic variables were employed as environmental variables for spatial prediction of soil PSFs. The results depicted that MRF gave satisfactory soil PSF prediction performance, where the R2 values were 0.62, 0.53, and 0.73 for sand, silt, and clay, respectively. Among the environmental variables, nighttime land surface temperature (LST_N) presented the highest importance in predicting soil PSFs in the Loess Plateau, China. Maps of soil PSFs and texture were generated at a 30 m resolution, which can be utilized as alternative data for soil erosion management and ecosystem conservation.

VIS-NIR spectroscopy and environmental factors coupled with PLSR models to predict soil organic carbon and nitrogen

Soil profile organic carbon (OC) and total nitrogen (TN) are influenced by topographic attributes, and land use. The visible and near-infrared (Vis-NIR) spectroscopy method can be used for the prediction of OC and TN because it is reliable, nondestructive, fast, and cost-effective. VIS-NIR soil spectral and environmental data were combined with the Partial least squares regression (PLSR) model to examine the effect of topography attributes and land use on topsoil and subsoil OC and TN stocks. After this, based on the soil depth, 114 soil samples were collected from 0 to 20 cm (topsoil) and 20–50 cm (subsoil) under three land uses, as well as OC and TN, along with several soil properties including soil particles (sand, silt, clay), pH, and bulk density in both topsoil and subsoil samples were measured. A DEM with a resolution of 30 m was used to derive the topography factors and remote sensing data was used to calculate the vegetation index. Soils (0–50 cm) under orchard land use had the highest stock of SOC (7.4 kg m−2) as well as TN (2.4 kg m−2). There was a significant increase in the organic matter stock of soils located on the south aspect (8.3 kg m−2) compared to soils located on other aspects, particularly on the north aspect (3.9% increase). Soils on the south aspect contain higher soil-water contents and lower temperatures, resulting in a decrease in the decomposition of soil organic matter. A strong positive correlation was demonstrated between topography wetness index (0.57–0.63) and topography TN stocks (0.54–0.66) as well as the highest loading score among terrain attributes, suggesting that topography is the primary factor controlling SOC stocks, particularly subsoil stocks. Additionally, we found that soils on the south-facing aspects (N aspects) had the highest spectra. Additionally, the PLSR, which showed an R2 of 0.82, a RMSE of 0.15 %, and a RPD of 0.39 indicated excellent prediction capabilities for the OC content. We concluded that the PLSR model coupled with Vis-NIR spectroscopy is able to predict topsoil and subsoil OC and N content under different aspect slopes.

Prediction of lead in agricultural soils: An integrated approach using machine learning, terrain attributes and reflectance spectra

The study aimed to predict lead (Pb) concentrations in agricultural soils by analyzing visible, near-infrared, and shortwave infrared (VNIR-SWIR) spectra and terrain attributes under three distinct approaches. Approach 1 relied solely on the VNIR-SWIR data, with the cubist_FD (cubist_first derivative) modeling technique as the most effective, achieving a coefficient of determination (R2) of 0.63, a concordance correlation coefficient (CCC) of 0.51, a mean absolute error (MAE) of 6.87 mg kg-1, and a root mean square error (RMSE) of 8.66 mg kg-1. Approach 2 combined VNIR-SWIR spectra and terrain attributes, where SNV (standard normal variate) preprocessing technique and extreme gradient boosting (EGB) yielded superior results with R2 of 0.75, CCC of 0.65, MAE of 5.48 mg kg-1, and minimal RMSE of 7.34 mg kg-1. Approach 3 solely employed terrain attributes, and the combination with cubist modeling demonstrated the best prediction results, with R2 of 0.75, CCC of 0.66, MAE of 6.18 mg kg-1, and RMSE of 7.71 mg kg-1. The cumulative assessment identified that the fusion of terrain properties, SNV-transformed VNIR-SWIR spectra, and EGB as the optimal method for estimating Pb concentrations in agricultural soil yielded the highest R2 value and minimal error. Comparatively, Gaussian process regression (GPR), artificial neural network (ANN), and support vector machine (SVM) techniques achieved high R2 values in approaches 2 and 3 but also exhibited higher estimation errors. In conclusion, the study underscores the significance of using relevant auxiliary datasets and appropriate modeling techniques for accurate Pb concentration predictions with minimal error in agricultural soils. The findings contribute valuable insights for developing successful soil management strategies based on predictive modeling.

Incorporating landscape ecological approach in machine learning classification for agricultural land-use mapping based on a single date imagery

Land-use maps containing crop rotational information are very important in land management and physical planning. Such maps are usually generated using multitemporal data. Although recent technology allows analysts to process multitemporal information effectively, the use of single date imagery for such purpose is more efficient. This study aimed to map detailed agricultural land-use with crop rotational information based on a single date Landsat 8 imagery and SRTM-derived terrain attributes. A landscape ecological approach assuming the influence of terrain characteristics on the existence of crop and land-use types was implemented in multisource classification using random decision forest (RDF) machine learning algorithm. The use of seven optical bands and five terrain attributes could provide a land-use map at 88.03% accuracy, compared to seven optical bands only that generate 82.45% accuracy. These results are also better than those of maximum likelihood. The most influential variables in the achieved accuracy are elevation and thermal band.

Estimating the spatial distribution of soil volumetric water content in an agricultural field employing remote sensing and other auxiliary data under different tillage management practices

AbstractKnowledge of soil volumetric water content (VWC) on agricultural soils as influenced by different soil management practices is important, but the measurement outputs of frequently used traditional sampling techniques are restricted to point‐based measurements with limited spatial coverage. Remote sensing (RS) techniques are therefore being explored because of their greater spatial and temporal availability as well as their ability to cover large‐scale areas. But a general limitation for RS data is the presence of vegetation cover, cloud cover and the effect of topography. To minimize the effects of these factors during field sampling, the use of spectral indices and terrain attributes have proven successful in the estimation of several soil properties; however, the impact of these approaches for the estimation and mapping of soil VWC, an important factor in crop growth and development, especially where different soil management practices are employed, remains limited. To contribute to the knowledge base of RS under varying soil systems, this study explores the possibility of combining in‐situ measurements with remotely sensed (explanatory variables) data obtained under four different tillage practices to produce an estimated soil VWC that represents the entire study field. The tillage practices used include reduced till (RT), strategic till (ST), no‐till (NT) and conventional till (CT). From these tillage plots, three explanatory datasets, namely Sentinel‐2 (S2), spectral indices (SI) and terrain attributes (TA), were collected as predictors. In addition, each of the explanatory variables was structured into four groups, representing each of the four tillage methods. The eXtreme Gradient Boosting (XGBoost) model was used, and the best results were selected based on the root mean squared error (RMSE), the coefficient of determination (R2) and the mean absolute error (MAE). Prior to soil VWC prediction, the Pearson correlation matrix was used to determine the linear relationship between each of the selected explanatory variables (S2 bands, SI and TA) and soil VWC. Furthermore, spatial distribution maps of soil VWC were constructed using the inverse distance weighting (IDW) interpolation technique. For soil VWC estimation, the TA outperformed the SI and S2 datasets (R2 = 0.84). Similarly, the spatial distribution maps obtained from the TA data show a study area with a large concentration of VWC compared with the other datasets. The study also identified CT as the tillage approach that most impacts soil VWC estimation because all predicted results were poor without the addition of data from the CT plot. According to our findings, using TA data collected from various tillage management systems to estimate soil VWC is very promising because they can be used as predictors to improve soil VWC estimation and mapping. This study demonstrates conclusively that remote sensing data collected from different tillage management systems can be used as predictors to enhance the estimation and mapping of soil VWC, complementing the basis for the development of reliable and consistent precision irrigation management systems.

Estimation of Landslide and Mudslide Susceptibility with Multi-Modal Remote Sensing Data and Semantics: The Case of Yunnan Mountain Area

Landslide and mudslide susceptibility predictions play a crucial role in environmental monitoring, ecological protection, settlement planning, etc. Currently, multi-modal remote sensing data have been used for precise landslide and mudslide disaster prediction with spatial details, spectral information, or terrain attributes. However, features regarding landslide and mudslide susceptibility are often hidden in multi-modal remote sensing images, beyond the features extracted and learnt by deep learning approaches. This paper reports our efforts to conduct landslide and mudslide susceptibility prediction with multi-modal remote sensing data involving digital elevation models, optical remote sensing, and an SAR dataset. Moreover, based on the results generated by multi-modal remote sensing data, we further conducted landslide and mudslide susceptibility prediction with semantic knowledge. Through the comparisons with the ground truth datasets created by field investigation, experimental results have proved that remote sensing data can only enhance deep learning techniques to detect the landslide and mudslide, rather than the landslide and mudslide susceptibility. Knowledge regarding the potential clues about landslide and mudslide, which would be critical for estimating landslide and mudslide susceptibility, have not been comprehensively investigated yet.

A scenario-based approach for immediate post-earthquake rockfall impact assessment

Different approaches exist to describe the seismic triggering of rockfalls. Statistical approaches rely on the analysis of local terrain properties and their empirical correlation with observed rockfalls. Conversely, deterministic, or physically based approaches, rely on the modeling of individual trajectories of boulders set in motion by seismic shaking. They require different data and allow various interpretations and applications of their results. Here, we present a new method for earthquake-triggered rockfall scenario assessment adopting ground shaking estimates, produced in near real-time by a seismological monitoring network. Its key inputs are the locations of likely initiation points of rockfall trajectories, namely, rockfall sources, obtained by statistical analysis of digital topography. In the model, ground shaking maps corresponding to a specific earthquake suppress the probability of activation of sources at locations with low ground shaking while enhancing that in areas close to the epicenter. Rockfall trajectories are calculated from the probabilistic source map by three-dimensional kinematic modeling using the software STONE. We apply the method to the 1976 MI = 6.5 Friuli earthquake, for which an inventory of seismically-triggered rockfalls exists. We suggest that using peak ground acceleration as a modulating parameter to suppress/enhance rockfall source probability, the model reasonably reproduces observations. Results allow a preliminary impact evaluation before field observations become available. We suggest that the framework may be suitable for rapid rockfall impact assessment as soon as ground-shaking estimates (empirical or numerical models) are available after a seismic event.