Search

Notwithstanding the overall improvement in the ecological condition of the Qilian Mountains, there are localized occurrences of grassland degradation, desertification, and salinization. Moreover, timely and accurate acquisition of desertification information is a fundamental prerequisite for effective monitoring and prevention of desertification. Leveraging the Google Earth Engine (GEE) platform in conjunction with machine learning techniques, this study aims to identify and extract the spatiotemporal dynamics of desertification in the Qilian Mountain National Park (QMNP) and its surroundings (QMNPs) spanning from 1988 to 2023. Results show that based on the random forest algorithm, the multi-index inversion methodology achieves a commendable overall accuracy of 91.9% in desertification extraction. From 1988 to 2023, the gravity center of light desertification shifts southeastward, while centers characterized by moderate, severe, and extremely severe desertification display a westward retreat with fluctuations. The area of sandy land shows an expansion trend in the medium term, but after 2018, desertification in QMNPs reversed. As of 2023, the sandy land area measured 16,897.35 km2, accounting for 18.29% of the total area of QMNPs. The insights garnered from this study provide a valuable reference for regional desertification prevention and control in the future. [ABSTRACT FROM AUTHOR]

Enriching and updating maps are among the most important tasks of any urban management organization for informed decision making. Urban cadastral map enrichment is a time-consuming and costly process, which needs an expert's opinion for quality control. This research proposes a smart framework to enrich a cadastral base map using a more up-to-date map automatically by machine learning algorithms. The proposed framework has three main steps, including parcel matching, parcel change detection and base map enrichment. The matching step is performed by checking the center point of each parcel in the other map parcels. Support vector machine and random forest classification algorithms are used to detect the changed parcels in the base map. The proposed models employ the genetic algorithm for feature selection and grey wolf optimization and Harris hawks optimization for hyperparameter optimization to improve accuracy and performance. By assessing the accuracies of the models, the random forest model with feature selection and grey wolf optimization, with an F1-score of 0.9018, was selected for the parcel change detection method. Finally, the detected changed parcels in the base map are deleted and relocated automatically with corresponding parcels in the more up-to-date map by the affine transformation. [ABSTRACT FROM AUTHOR]

Amid the global shift towards sustainable development, this study addresses the burgeoning electric vehicle (EV) market and its infrastructure challenges, particularly the lag in public charging facility development. Focusing on Wuhan, it utilizes big data to analyze EV charging behavior's spatiotemporal aspects and the urban environment's influence on charging efficiency. Employing a random forest regression and multiscale geographically weighted regression (MGWR), the research elucidates the nonlinear interaction between urban infrastructure and charging station usage. Key findings include (1) a direct correlation between EV charging patterns and urban temporal factors, with notable price elasticity; (2) the predominant influence of commuting distance, supplemented by the availability of fast-charging options; and (3) a strategic proposal for increasing slow-charging facilities at key urban locations to balance operational costs and user demand. The study combines spatial analysis and charging behavior to recommend enhancements in public EV charging infrastructure layouts. [ABSTRACT FROM AUTHOR]

Based on the data from two field surveys in 2015 and 2022, this paper calculates the weight of values using the entropy weight method and the variation coefficient method, and evaluates risk using the information quantity method. The information quantities of four levels of criteria (hazards, exposure, vulnerability, emergency responses, and capability of recovery) were extracted and inputted into a random forest model. After optimizing the hyperparameters of the random forest using GridSearchCV, the risk assessment was performed again. Finally, the accuracy of the two evaluation results was verified using an ROC curve, and the model with the higher AUC value was selected to create a risk map. Compared with previous studies, this paper considers the factors of emergency responses and recovery capability, which makes the risk assessment more comprehensive. Our findings show that the evaluation results based on the coupling model are more accurate than the evaluation results of the information method, as the coupling model had an AUC value of 0.9329. After considering the indices of emergency responses and capability of recovery, the risk level of the highest-risk area in the study area decreased. [ABSTRACT FROM AUTHOR]

Accurate spatial distribution of gridded gross domestic product (GDP) data is crucial for revealing regional disparities within administrative units, thus facilitating a deeper understanding of regional economic dynamics, industrial distribution, and urbanization trends. The existing GDP spatial models often rely on prediction residuals for model evaluation or utilize residual distribution to improve the final accuracy, frequently overlooking the modifiable areal unit problem within residual distribution. This paper introduces a hybrid downscaling model that combines random forest and area-to-area kriging to map gridded GDP. Employing Thailand as a case study, GDP distribution maps were generated at a 1 km spatial resolution for the year 2015 and compared with five alternative downscaling methods and an existing GDP product. The results demonstrate that the proposed approach yields higher accuracy and greater precision in detailing GDP distribution, as evidenced by the smallest mean absolute error and root mean squared error values, which stand at USD 256.458 and 699.348 ten million, respectively. Among the four different sets of auxiliary variables considered, one consistently exhibited a higher prediction accuracy. This particular set of auxiliary variables integrated classification-based variables, illustrating the advantages of incorporating such integrated variables into modeling while accounting for classification characteristics. [ABSTRACT FROM AUTHOR]

Population growth in urban centres and the intensification of segregation phenomena associated with international mobility require improved urban planning and decision-making. More effective planning in turn requires better analysis and geospatial modelling of residential locations, along with a deeper understanding of the factors that drive the spatial distribution of various migrant groups. This study examines the factors that influence the distribution of migrants at the local level and evaluates their importance using machine learning, specifically the variable importance measures produced by the random forest algorithm. It is conducted on high spatial resolution ( 100 × 100 grid cells) register data in Amsterdam and Copenhagen, using demographic, housing and neighbourhood attributes for 2018. The results distinguish the ethnic and demographic composition of a location as an important factor in the residential distribution of migrants in both cities. We also examine whether certain migrant groups pay higher prices in the most attractive areas, using spatial statistics and mapping for 2008 and 2018. We find evidence of segregation in both cities, with Western migrants having higher purchasing power than non-Western migrants in both years. The method sheds light on the determinants of migrant distribution in destination cities and advances our understanding of the application of geospatial artificial intelligence to urban dynamics and population movements. [ABSTRACT FROM AUTHOR]

Geographical indication (GI) offers a unique protection scheme to preserve high-quality agricultural products and support rural sustainability at the territorial level. However, not all the areas with traditional agricultural products are acknowledged with a GI. Quantifying the contribution of each factor to geographical indication agricultural products (GIAPs) can facilitate the formulation of effective policies to improve rural livelihoods. In this study, the random forest (RF) model was applied to investigate the contribution of multi-perspective factors, including nature, society, agriculture and market, on the distribution of GIAPs, and examined the driving causes using interpretable approaches. The empirical findings demonstrate that the RF model is able to accurately capture most of the important factors characterizing GIAPs and to make out-of-sample predictions of the study units which obtain GIs. This study revealed that natural conditions and market demand were contributing aspects to the disparity of GIAPs in Northeast China. The order of determinants was the category of online GIAPs (CatOn) > the number of online GIAPs (NumOn) > the area of black soil (BlaSoil) > the distance to offline stores selling GIAPs (DisOff). Of these, GIAPs was lower than y b a s e in parts of districts of Jilin and Heilongjiang Provinces when the area of black soil (BlaSoil) gradually increased. When the category and number of online GIAPs (CatOn and NumOn) were less than 20 and 5, respectively, GIAPs were enhanced, especially for 40% of the districts in Liaoning Province. Deepening understanding of GIAPs helps to better target and tailor sustainable development policies. [ABSTRACT FROM AUTHOR]

The development and functional perfection of urban areas have led to increasingly severe fire risks in recent decades. Previous urban fire risk assessment methods relied on subjective judgment, rough data collection, simple linear statistical methods, etc. These drawbacks can lead to low robustness of evaluation and inadequate generalization ability. To resolve these problems, this paper selects the indicator and regression models based on the high-resolution data of the spatial distribution characteristics of Longquanyi distinct in Chengdu, China. and proposes an integrated machine learning algorithm for fire risk assessment. Firstly, the kernel density analysis is used to map the fourteen urban characteristics related to fire risks. The contributions of these indicators (characteristics) to fire risk and its corresponding index are determined by Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and eXtreme Gradient Boosting (XGBoost). Then, the spatial correlation of fire risks is determined through Moran's I, and the spatial distribution pattern of indicator weights is clarified through the raster coefficient space analysis. Finally, with these selected indicators, we test the regression performance with a backpropagation neural network (BPNN) algorithm and a geographically weighted regression (GWR) model. The results indicate that numerical variables are more suitable than dummy variables for estimating micro-scale fire risks. The main factors with a high contribution are all numerical variables, including roads, gas pipelines, GDP, hazardous chemical enterprises, petrol and charging stations, cultural heritage protection units, assembly occupancies, and high-rise buildings. The machine learning algorithm integrating RF and BPNN shows the best performance (R2 = 0.97), followed by the RF-GWR integrated algorithm (R2 = 0.87). Compared with previous methods, this algorithm reduces the subjectivity of the traditional assessment models and shows the ability to automatically obtain the key indicators of urban fire risks. Hence, this new approach provides us with a more robust tool for assessing the future fire safety level in urban areas. [ABSTRACT FROM AUTHOR]

Based on a study of the spatial distribution of coffee shops in the main urban area of Beijing, the main influencing factors were selected based on the multi-source space data. Subsequently, three regression models were compared, and the best site selection model was found. A comparison was performed between the prediction model functioning with a buffer and without one, and the accuracy of the location model was verified by comparing the actual change trend and the predicted trend in two years. The following conclusions were obtained: (1) coffee shops in the main urban area of Beijing are clustered in an area within 12 km of the main urban center, and also around the core commercial agglomeration area; (2) the random forest (RF) model is the best model in this study, and the accuracy values before and after buffer analysis were 0.915 and 0.929, respectively; and (3) after verifying the accuracy of the model through two years of data, we recommend the establishment of a main road buffer zone for site selection, and the success rate of site selection was found to reach 72.97%. This study provides crucial insight for coffee shop prediction model selection and potential store location selection, which is significant to improving the layout of leisure spaces and promoting economic development. [ABSTRACT FROM AUTHOR]

Rural tourism has long been recognized as a significant strategy for promoting rural revitalization in China. Excessive development has had a number of negative consequences for rural tourism. As a result, there is a growing need to optimize the developmental framework of rural tourism in order to ensure its sustainable growth. This study focuses on key tourism villages and employs geostatistical analysis and the random forest methodology to elucidate the spatial mechanisms underlying rural tourism and identify potential areas for its development in China. The research findings reveal several important insights: (1) Key tourism villages exhibit a concentrated spatial distribution, characterized by pronounced regional disparities. (2) The intrinsic characteristics of rural areas and the conditions conducive to tourism development play pivotal roles in shaping rural tourism. Notably, cultural resources, tourism resources, rural accessibility, and tourism potential are identified as the primary influential factors. (3) Predictive modeling using random forest analysis indicates that densely populated areas in the eastern region retain the highest level of suitability for rural tourism. In contrast, the development of rural tourism in western and border regions encounters certain constraints. Additionally, the northern region encompasses larger expanses with high suitability, whereas the southern region is generally moderate. This comprehensive nationwide investigation provides valuable insights into the key aspects of rural tourism development and offers practical guidance for achieving sustainable rural tourism practices in China. [ABSTRACT FROM AUTHOR]

Black carbon (BC) is a significant source of air pollution since it impacts public health and climate change. Understanding its distribution in the complex urban environment is challenging. We integrated a land use model with four machine learning models to estimate traffic-related BC concentrations in Oakland, CA. Random Forest was the best-performing model, with regression coefficient (R2) values of 0.701 on the train set and 0.695 on the validation set with a root mean square error (RMSE) of 0.210 mg/m3. Vehicle speed and local road systems were the most sensitive variables in estimating BC concentrations. However, this approach was inefficient at identifying hyperlocal hotspots, especially in a complex urban environment where highways and truck routes are significant emission sources. Using the land use method to estimate BC concentrations may lead to underestimating some localized hotspots. This work can improve air quality exposure assessment for vulnerable populations and help emphasize potential environmental justice issues. [ABSTRACT FROM AUTHOR]

The evaluation of satellite soil moisture is a big challenge owing to the large spatial mismatch between pixel-based satellite soil moisture products and point-based in situ measurements. Upscaling in situ measurements to obtain the "true value" of soil moisture content at the satellite grid/footprint scale can make up for the scale difference and improve the validation. Many existing upscaling methods have strict requirements regarding the spatial distribution and quantity of soil moisture sensors. However, in reality, soil-moisture-monitoring networks are commonly sparse with low sensor density, which increases the difficulty of obtaining accurate upscaled soil moisture data and limits the validation of satellite products. For this reason, this paper proposes a scheme to upscale in situ measurements using five machine learning methods along with Landsat 8 datasets and DEM data to validate the accuracy of a SMAP-enhanced passive soil moisture product for a sparse network on the Qinghai–Tibet Plateau. The proposed scheme realizes the upscaling of in situ soil moisture data to the pixel scale (30 m × 30 m) and then to the coarse grid scale (9 km × 9 km) by using multi-source remote sensing data as the bridge of scale conversion. The long-time SMAP SM products since April 2015 on the Qinghai–Tibet Plateau were validated based on upscaled soil moisture data. The results show that (1) random forest regression performs the best, and the upscaled soil moisture data reflect the region-average soil moisture conditions that can be used for evaluating SMAP data; (2) the SMAP product meets its scientific measurement requirements; and (3) the SMAP product generally underestimates the soil moisture in the study area. [ABSTRACT FROM AUTHOR]

The inefficient use of urban resources and the imbalance of spatial structures make optimizing land use management a top priority in urban environmental management. Traditional land use classification systems that prioritize only natural features while disregarding human activity can result in redundancy and conflicts in urban planning. The Production–Living–Ecological Space (PLES) approach was developed as an integrated method for territorial spatial classification. However, most existing studies on PLES are conducted at provincial scales, largely overlooking fine-scale usage within cities. In addition, the existing concept of PLES has been vaguely defined, resulting in linear and simple identification methods that are not applicable to complex urban environments. To address these issues, this study proposes a method to identify urban PLES based on supervised classification using random forest models, which integrate empirical knowledge and multi-source heterogeneous information. The experiments conducted in Haikou reveal the regional aggregation of living and production spaces and the scarcity of ecological space in the city. Our study proposes a concrete concept of PLES and a method for identifying PLES that can be applied to multiple regions, providing an effective tool for the coordinated management of urban production, living, and ecological environments. [ABSTRACT FROM AUTHOR]

Road accidents are a worldwide problem, affecting millions of people annually. One way to reduce such accidents is to predict risk areas and alert drivers. Advanced research has been carried out on identifying accident-influencing factors and potential highway risk areas to mitigate the number of road accidents. Machine learning techniques have been used to build prediction models using a supervised classification based on a labeled dataset. In this work, we experimented with many machine learning algorithms to discover the best classifier for the Brazilian federal road hotspots associated with severe or nonsevere accident risk using several features. We tested with SVM, random forest, and a multi-layer perceptron neural network. The dataset contains a ten-year road accident report by the Brazilian Federal Highway Police. The feature set includes spatial footprint, weekday and time when the accident happened, road type, route, orientation, weather conditions, and accident type. The results were promising, and the neural network model provided the best results, achieving an accuracy of 83%, a precision of 84%, a recall of 83%, and an F1-score of 82%. [ABSTRACT FROM AUTHOR]

Law enforcement agencies continue to grow in the use of spatial analysis to assist in identifying patterns of outcomes. Despite the critical nature of proper resource allocation for mental health incidents, there has been little progress in statistical modeling of the geo-spatial nature of mental health events in Little Rock, Arkansas. In this article, we provide insights into the spatial nature of mental health data from Little Rock, Arkansas between 2015 and 2018, under a supervised spatial modeling framework. We provide evidence of spatial clustering and identify the important features influencing such heterogeneity via a spatially informed hierarchy of generalized linear, tree-based, and spatial regression models, viz. the Poisson regression model, the random forest model, the spatial Durbin error model, and the Manski model. The insights obtained from these different models are presented here along with their relative predictive performances. The inferential tools developed here can be used in a broad variety of spatial modeling contexts and have the potential to aid both law enforcement agencies and the city in properly allocating resources. We were able to identify several built-environment and socio-demographic measures related to mental health calls while noting that the results indicated that there are unmeasured factors that contribute to the number of events. [ABSTRACT FROM AUTHOR]

Landslide susceptibility assessment (LSA) based on machine learning methods has been widely used in landslide geological hazard management and research. However, the problem of sample imbalance in landslide susceptibility assessment, where landslide samples tend to be much smaller than non-landslide samples, is often overlooked. This problem is often one of the important factors affecting the performance of landslide susceptibility models. In this paper, we take the Wanzhou district of Chongqing city as an example, where the total number of data sets is more than 580,000 and the ratio of positive to negative samples is 1:19. We oversample or undersample the unbalanced landslide samples to make them balanced, and then compare the performance of machine learning models with different sampling strategies. Three classic machine learning algorithms, logistic regression, random forest and LightGBM, are used for LSA modeling. The results show that the model trained directly using the unbalanced sample dataset performs the worst, showing an extremely low recall rate, indicating that its predictive ability for landslide samples is extremely low and cannot be applied in practice. Compared with the original dataset, the sample set optimized through certain methods has demonstrated improved predictive performance across various classifiers, manifested in the improvement of AUC value and recall rate. The best model was the random forest model using over-sampling (O_RF) (AUC = 0.932). [ABSTRACT FROM AUTHOR]

Gridded gross domestic product (GDP) data are a crucial land surface parameter for many geoscience applications. Recently, machine learning approaches have become powerful tools in generating gridded GDP data. However, most machine learning approaches for gridded GDP estimation seldom consider the geographical properties of input variables. Therefore, in this study, a geographically weighted stacking ensemble learning approach was developed to generate gridded GDP data. Three algorithms—random forest, XGBoost, and LightGBM—were used as base models, and the linear regression in stacking ensemble learning was replaced by geographically weighted regression to locally fuse the three predictions. A case study was conducted in China to demonstrate the effectiveness of the proposed approach. The results showed that the proposed GDP downscaling approach outperformed the three base models and traditional stacking ensemble learning. Meanwhile, it had good predictive power on county-level GDP test data with R2 of 0.894, 0.976, and 0.976 for the primary, secondary, and tertiary sectors, respectively. Moreover, the predicted 1 km gridded GDP data had a high accuracy (R2 = 0.787) when evaluated by town-level GDP data. Hence, the proposed GDP downscaling approach provides a valuable option for generating gridded GDP data. The generated 1 km gridded GDP data of China from 2020 are of great significance for other applications. [ABSTRACT FROM AUTHOR]

Land use and land cover changes driven by urban sprawl has accelerated the degradation of ecosystem services in metropolitan settlements. However, most optimisation techniques do not consider the dynamic effect of urban sprawl on the spatial criteria on which decisions are based. In addition, integrating the current simulation approach with land use optimisation approaches to make a sustainable decision regarding the suitable site encompasses complex processes. Thus, this study aims to innovate a novel technique that can predict urban sprawl for a long time and can be simply integrated with optimisation land use techniques to make suitable decisions. Three main processes were applied in this study: (1) a supervised classification process using random forest (RF), (2) prediction of urban growth using a hybrid method combining an artificial neural network and cellular automata and (3) the development of a novel machine learning (ML) model to predict urban growth boundaries (UGBs). The ML model included linear regression, RF, K-nearest neighbour and AdaBoost. The performance of the novel ML model was effective, according to the validation metrics that were measured by the four ML algorithms. The results show that the Nasiriyah City expansion (the study area) is haphazard and unplanned, resulting in disastrous effects on urban and natural systems. The urban area ratio was increased by about 10%, i.e., from 2.5% in the year 1992 to 12.2% in 2022. In addition, the city will be expanded by 34%, 25% and 19% by the years 2032, 2042 and 2052, respectively. Therefore, this novel technique is recommended for integration with optimisation land use techniques to determine the sites that would be covered by the future city expansion. [ABSTRACT FROM AUTHOR]

In order to address the challenges of global warming, the Billion Tree plantation drive was initiated by the government of Khyber Pakhtunkhwa, Pakistan, in 2014. The land cover changes as a result of Billion Tree Tsunami project are relatively unexplored. In particular, the utilization of remote sensing techniques and satellite image classification has not yet been done. Recently, the Sentinel-2 (S2) satellite has found much utilization in remote sensing and land cover classification. Sentinel-2 (S2) sensors provide freely available images with a spatial resolution of 10, 20 and 60 m. The higher classification accuracy is directly dependent on the higher spatial resolution of the images. This research aims to classify the land cover changes as a result of the Billion Tree plantation drive in the areas of our interest using Random Forest Classifier (RFA) and image fusion techniques applied to Sentinel-2 and Landsat-8 satellite images. A state-of-the-art, model-based image-sharpening technique was used to sharpen the lower resolution Sentinel-2 bands to 10 m. Then the RFA classifier was used to classify the sharpened images and an accuracy assessment was performed for the classified images of the years 2016, 2018, 2020 and 2022. Finally, ground data samples were collected using an unmanned aerial vehicle (UAV) drone and the classified image samples were compared with the real data collected for the year 2022. The real data ground samples were matched by more than 90% with the classified image samples. The overall classification accuracies [%] for the classified images were recorded as 92.87%, 90.79%, 90.27% and 93.02% for the sample data of the years 2016, 2018, 2020 and 2022, respectively. Similarly, an overall Kappa hat classification was calculated as 0.87, 0.86, 0.83 and 0.84 for the sample data of the years 2016, 2018, 2020 and 2022, respectively. [ABSTRACT FROM AUTHOR]

One hundred seventeen landslides occurred in Malang Regency throughout 2021, triggering the need for practical hazard assessments to strengthen the disaster mitigation process. In terms of providing a solution for investigating the location of landslides more precisely, this research aims to compare machine learning algorithms to produce an accurate landslide susceptibility model. This research applies three machine learning algorithms composed of RF (random forest), NB (naïve Bayes), and KNN (k-nearest neighbor) and 12 conditioning factors. The conditioning factors consist of slope, elevation, aspect, NDVI, geological type, soil type, distance from the fault, distance from the river, river density, TWI, land cover, and annual rainfall. This research performs seven models over three ratios between the training and testing dataset encompassing 50:50, 60:40, and 70:30 for KNN and NB algorithms and 70:30 for the RF algorithm. This research measures the performance of each model using eight parameters (ROC, AUC, ACC, SN, SP, BA, GM, CK, and MCC). The results indicate that RF 70:30 generates the best performance, witnessed by the evaluation parameters ACC (0.884), SN (0.765), GM (0.863), BA (0.857), CK (0.749), MCC (0.876), and AUC (0.943). Overall, seven models have reasonably good accuracy, ranging between 0.806 and 0.884. Furthermore, based on the best model, the study area is dominated by high susceptibility with an area coverage of 51%, which occurs in the areas with high slopes. This research is expected to improve the quality of landslide susceptibility maps in the study area as a foundation for mitigation planning. Furthermore, it can provide recommendations for further research in splitting ratio scenarios between training and testing data. [ABSTRACT FROM AUTHOR]

Some studies have established relationships between neighborhood conditions and health. However, they neither evaluate the relative importance of neighborhood components in increasing obesity nor, more crucially, how these neighborhood factors vary geographically. We use the geographical random forest to analyze each factor's spatial variation and contribution to explaining tract-level obesity prevalence in Chicago, Illinois, United States. According to our findings, the geographical random forest outperforms the typically used nonspatial random forest model in terms of the out-of-bag prediction accuracy. In the Chicago tracts, poverty is the most important factor, whereas biking is the least important. Crime is the most critical factor in explaining obesity prevalence in Chicago's south suburbs while poverty appears to be the most important predictor in the city's south. For policy planning and evidence-based decision-making, our results suggest that social and ecological patterns of neighborhood characteristics are associated with obesity prevalence. Consequently, interventions should be devised and implemented based on local circumstances rather than generic notions of prevention strategies and healthcare barriers that apply to Chicago. [ABSTRACT FROM AUTHOR]

Recognizing the patterns of road junctions in a road network plays a crucial role in various applications. Owing to the diversity and complexity of morphologies of road junctions, traditional methods that rely heavily on manual settings of features and rules are often problematic. In recent years, several studies have employed convolutional neural networks (CNNs) to classify complex junctions. These methods usually convert vector-based junctions into raster representations with a predefined sampling area coverage. However, a fixed sampling area coverage cannot ensure the integrity and clarity of each junction, which inevitably leads to misclassification. To overcome this drawback, this study proposes a stacking ensemble learning method for classifying the patterns of complex road junctions. In this method, each junction is first converted into raster images with multiple area coverages. Subsequently, several CNN-based base-classifiers are trained using raster images, and they output the probabilities of the junction belonging to different patterns. Finally, a meta-classifier based on random forest is used to combine the outputs of the base-classifiers and learn to arrive at the final classification. Experimental results show that the proposed method can improve the classification accuracy for complex road junctions compared to existing CNN-based classifiers that are trained using raster representations of junctions with a fixed sampling area coverage. [ABSTRACT FROM AUTHOR]

With population ageing being a notable demographic phenomenon, aging in place is an efficient model to accommodate the mounting aging needs. Based on the community scale, this study takes the 15-min community-life circle as the basic research unit to investigate the imbalanced distribution of pension resources and its influencing factors in downtown Shanghai. We obtained six types of elderly care facilities data from the Shanghai elderly care service platform and utilized the Gaussian 2-step Floating Catchment Area method to calculate the accessibility of 6-type elderly care facilities. Then, we used the Entropy Weight Method to calculate the comprehensive accessibility of elderly care facilities. The Getis–Ord Gi* method was adopted to analyze the overall distribution, identifying the well-developed and the under-developed areas. To explore the influencing factors of the distribution, this paper obtained multi-source data to construct a total of 17 indicators and established a Random Forest model to identify the feature importance. With the selected eight factors, the Geographically Weighted Regression (GWR) model was applied to study the spatial heterogeneity of influencing factors, and the model showed a good performance with the AdjR2 being 0.8364. The findings of this research reveal the following: (1) The distribution of six types of elderly care facilities is extremely uneven, with obvious spatial aggregation characteristics. Amongst the seven administrative regions, Huangpu District has the best accessibility to pension resources, while the resources in the other six regions are highly inadequate. (2) Essential influencing factors of the comprehensive accessibility of community-based elderly care facilities are accessibility of nursing institutions (positive), hotel density (positive), catering density (negative), education density (positive) and medical density (negative), while "rents", "plot ratio" and "building density" have little impact on comprehensive accessibility. (3) The results of GWR revealed that the eight indicators are heterogeneous in space, all of which have bidirectional effects on comprehensive accessibility. By investigating the spatial distribution patterns and influencing factors of pension resources in Shanghai, this research could further contribute to establishing a sound community-based elderly care service system that improves older adults' quality of life and promotes social fairness and justice. [ABSTRACT FROM AUTHOR]

Many countries, including China, have implemented the spatial government policy widely known as urban growth boundary (UGB) for managing future urban growth. However, few studies have asked why we need UGB, especially pre-evaluating the utility of UGB for reshaping the future spatial patterns of cities. In this research, we proposed a constrained urban growth simulation model (CUGSM) which coupled Markov chain (MC), random forest (RF), and patch growth based cellular automata (Patch-CA) to simulate urban growth. The regulatory effect of UGB was coupled with CUGSM based on a random probability game method. Guangzhou city, a metropolitan area located in the Peral River Delta of China, was taken as a case study. Historical urban growth from 1995 to 2005 and random forests were used to calibrate the conversion rules of Patch-CA, and the urban patterns simulated and observed in 2015 were used to identify the simulation accuracy. The results showed that the Kappa and figure of merit (FOM) indices of the unconstrained Patch-CA were just 0.7914 and 0.1930, respectively, which indicated that the actual urban growth was reshaped by some force beyond what Patch-CA has learned. We further compared the simulation scenarios in 2035 with and without considering the UGB constraint, and the difference between them is as high as 21.14%, which demonstrates that UGB plays an important role in the spatial reshaping of future urban growth. Specifically, the newly added urban land outside the UGB has decreased from 25.13% to 16.86% after considering the UGB constraint; particularly, the occupation of agricultural space and ecological space has been dramatically reduced. This research has demonstrated that the utility of UGB for reshaping future urban growth is pronounced, and it is necessary for the Chinese government to further strengthen UGB policy to promote sustainable urban growth. [ABSTRACT FROM AUTHOR]

The aim of this paper is to present developments of an advanced geospatial analytics algorithm that improves the prediction power of a random forest regression model while addressing the issue of spatial dependence commonly found in geographical data. We applied the methodology to a simple model of mean household income in the European Union regions to allow easy understanding and reproducibility of the analysis. The results are encouraging and suggest an improvement in the prediction power compared to previous techniques. The algorithm has been implemented in R and is available in the updated version of the SpatialML package in the CRAN repository. [ABSTRACT FROM AUTHOR]

The Mara River Basin of Africa has a world-famous ecosystem with vast vegetation, which is home to many wild animals. However, the basin is experiencing vegetation degradation and bad climate change, which has caused conflicts between people and wild animals, especially in dry seasons. This paper studied the vegetation greenness (VG), vegetation greenness trends (VGT), and their responses to climate change in dry seasons in the Mara River Basin, Africa. Firstly, based on Google Earth Engine (GEE) platform and Sentinel-2 images, the vegetation distribution map of the Mara River Basin was drawn. Then dry seasons MODIS NDVI data (January to February and June to September) were used to analyze the VGT. Finally, a random forest regression algorithm was used to evaluate the response of VG and VGT to temperature and precipitation derived from ERA5 from 2000 to 2019 at a resolution of 250 m. The results showed that the VGT was fluctuating in dry seasons, and the spatial differentiation was obvious. The greenness increasing trends both upstream and downstream were significantly larger than that of in the midstream. The responses of VG to precipitation were almost twice larger than temperature, and the responses of VGT to temperature were about 1.5 times larger than precipitation. The climate change trend of rising temperature and falling precipitation will lead to the degradation of vegetation and the reduction of crop production. There will be a vegetation degradation crisis in dry seasons in the Mara River Basin in the future. Identifying the spatiotemporal changes of VGT in dry seasons will be helpful to understand the response of VG and VGT to climate change and could also provide technical support to cope with climate-change-related issues for the basin. [ABSTRACT FROM AUTHOR]

Crimes are a common societal concern impacting quality of life and economic growth. Despite the global decrease in crime statistics, specific types of crime and feelings of insecurity, have often increased, leading safety and security agencies with the need to apply novel approaches and advanced systems to better predict and prevent occurrences. The use of geospatial technologies, combined with data mining and machine learning techniques allows for significant advances in the criminology of place. In this study, official police data from Porto, in Portugal, between 2016 and 2018, was georeferenced and treated using spatial analysis methods, which allowed the identification of spatial patterns and relevant hotspots. Then, machine learning processes were applied for space-time pattern mining. Using lasso regression analysis, significance for crime variables were found, with random forest and decision tree supporting the important variable selection. Lastly, tweets related to insecurity were collected and topic modeling and sentiment analysis was performed. Together, these methods assist interpretation of patterns, prediction and ultimately, performance of both police and planning professionals. [ABSTRACT FROM AUTHOR]

Geostatistical estimation methods rely on experimental variograms that are mostly erratic, leading to subjective model fitting and assuming normal distribution during conditional simulations. In contrast, Machine Learning Algorithms (MLA) are (1) free of such limitations, (2) can incorporate information from multiple sources and therefore emerge with increasing interest in real-time resource estimation and automation. However, MLAs need to be explored for robust learning of phenomena, better accuracy, and computational efficiency. This paper compares MLAs, i.e., Multiple Linear Regression (MLR) and Random Forest (RF), with Ordinary Kriging (OK). The techniques were applied to the publicly available Walkerlake dataset, while the exhaustive Walker Lake dataset was validated. The results of MLR were significant (p < 10 × 10−5), with correlation coefficients of 0.81 (R-square = 0.65) compared to 0.79 (R-square = 0.62) from the RF and OK methods. Additionally, MLR was automated (free from an intermediary step of variogram modelling as in OK), produced unbiased estimates, identified key samples representing different zones, and had higher computational efficiency. [ABSTRACT FROM AUTHOR]

Mapping of landslides, conducted in 2021 by the Geological Survey of Denmark and Greenland (GEUS), revealed 3202 landslides in Denmark, indicating that they might pose a bigger problem than previously acknowledged. Moreover, the changing climate is assumed to have an impact on landslide occurrences in the future. The aim of this study is to conduct the first landslide susceptibility mapping (LSM) in Denmark, reducing the geographical bias existing in LSM studies, and to identify areas prone to landslides in the future following representative concentration pathway RCP8.5, based on a set of explanatory variables in an area of interest located around Vejle Fjord, Jutland, Denmark. A subset from the landslide inventory provided by GEUS is used as ground truth data. Three well-established machine learning (ML) algorithms—Random Forest, Support Vector Machine, and Logistic Regression—were trained to classify the data samples as landslide or non-landslide, treating the ML task as a binary classification and expressing the results in the form of a probability in order to produce susceptibility maps. The classification results were validated through the test data and through an external data set for an area located outside of the region of interest. While the high predictive performance varied slightly among the three models on the test data, the LR and SVM demonstrated inferior accuracy outside of the study area. The results show that the RF model has robustness and potential for applicability in landslide susceptibility mapping in low-lying landscapes of Denmark in the present. The conducted mapping can become a step forward towards planning for mitigative and protective measures in landslide-prone areas in Denmark, providing policy-makers with necessary decision support. However, the map of the future climate change scenario shows the reduction of the susceptible areas, raising the question of the choice of the climate models and variables in the analysis. [ABSTRACT FROM AUTHOR]

Crime issues have been attracting widespread attention from citizens and managers of cities due to their unexpected and massive consequences. As an effective technique to prevent and control urban crimes, the data-driven spatial–temporal crime prediction can provide reasonable estimations associated with the crime hotspot. It thus contributes to the decision making of relevant departments under limited resources, as well as promotes civilized urban development. However, the deficient performance in the aspect of the daily spatial–temporal crime prediction at the urban-district-scale needs to be further resolved, which serves as a critical role in police resource allocation. In order to establish a practical and effective daily crime prediction framework at an urban police-district-scale, an "online" integrated graph model is proposed. A residual neural network (ResNet), graph convolutional network (GCN), and long short-term memory (LSTM) are integrated with an attention mechanism in the proposed model to extract and fuse the spatial–temporal features, topological graphs, and external features. Then, the "online" integrated graph model is validated by daily theft and assault data within 22 police districts in the city of Chicago, US from 1 January 2015 to 7 January 2020. Additionally, several widely used baseline models, including autoregressive integrated moving average (ARIMA), ridge regression, support vector regression (SVR), random forest, extreme gradient boosting (XGBoost), LSTM, convolutional neural network (CNN), and Conv-LSTM models, are compared with the proposed model from a quantitative point of view by using the same dataset. The results show that the predicted spatial–temporal patterns by the proposed model are close to the observations. Moreover, the integrated graph model performs more accurately since it has lower average values of the mean absolute error (MAE) and root mean square error (RMSE) than the other eight models. Therefore, the proposed model has great potential in supporting the decision making for the police in the fields of patrolling and investigation, as well as resource allocation. [ABSTRACT FROM AUTHOR]

Poverty statistics are conventionally compiled using data from socioeconomic surveys. This study examines an alternative approach to estimating poverty by investigating whether readily available geospatial data can accurately predict the spatial distribution of poverty in Thailand. In particular, the geospatial data examined in this study include the intensity of night-time light (NTL), land cover, vegetation index, land surface temperature, built-up areas, and points of interest. The study also compares the predictive performance of various econometric and machine-learning methods such as generalized least squares, neural network, random forest, and support-vector regression. Results suggest that the intensity of NTL and other variables that approximate population density are highly associated with the proportion of an area's population that are living in poverty. The random forest technique yielded the highest level of prediction accuracy among the methods considered in this study, primarily due to its capability to fit complex association structures even with small-to-medium-sized datasets. This obtained result suggests the potential applications of using publicly accessible geospatial data and machine-learning methods for timely monitoring of the poverty distribution. Moving forward, additional studies are needed to improve the predictive power and investigate the temporal stability of the relationships observed. [ABSTRACT FROM AUTHOR]

Landslide susceptibility assessment serves as a critical scientific reference for geohazard control, land use, and sustainable development planning. The existing research has not fully considered the potential impact of the spatial agglomeration and dispersion of landslides on assessments. This issue may cause a systematic evaluation bias when the field investigation data are insufficient, which is common due to limited human resources. Accordingly, this paper proposes two novel strategies, including a clustering algorithm and a preprocessing method, for these two ignored features to strengthen assessments, especially in high-susceptibility regions. Multiple machine learning models are compared in a case study of the city of Bijie (Guizhou Province, China). Then we generate the optimal susceptibility map and conduct two experiments to test the validity of the proposed methods. The primary conclusions of this study are as follows: (1) random forest (RF) was superior to other algorithms in the recognition of high-susceptibility areas and the portrayal of local spatial features; (2) the susceptibility map incorporating spatial feature messages showed a noticeable improvement over the spatial distribution and gradual change of susceptibility, as well as the accurate delineation of critical hazardous areas and the interpretation of historical hazards; and (3) the spatial distribution feature had a significant positive effect on modeling, as the accuracy increased by 5% and 10% after including the spatial agglomeration and dispersion consideration in the RF model, respectively. The benefit of the agglomeration is concentrated in high-susceptibility areas, and our work provides insight to improve the assessment accuracy in these areas, which is critical to risk assessment and prevention activities. [ABSTRACT FROM AUTHOR]

This paper aims to present possible areas to plant different vegetation types near traffic jams to reduce air pollution in the capital of Croatia, the city of Zagreb. Based on main traffic road and random forest machine learning using WorldView-2 European cities data, potential areas are established. It is seen that, based on a 10 m buffer, there is a possible planting area of more than 220,000 square meters, and based on 15 m buffer, there is a possible planting area of more than 410,000 square meters. The proposed plants are Viburnum lucidum, Photinia x fraseri, Euonymus japonicus, Tilia cordata, Aesculus hippocastanum, Pinus sp., Taxus baccata, Populus alba, Quercus robur, Betula pendula, which are characteristic for urban areas in Croatia. The planting of proposed trees may result in an increase of 3–5% in the total trees in the city of Zagreb. Although similar research has been published, this paper presents novelty findings from combined machine learning methods for defining green urban areas. Additionally, this paper presents original results for this region. [ABSTRACT FROM AUTHOR]

The classification of unmanned aerial vehicle hyperspectral images is of great significance in agricultural monitoring. This paper studied a fine classification method for crops based on feature transform combined with random forest (RF). Aiming at the problem of a large number of spectra and a large amount of calculation, three feature transform methods for dimensionality reduction, minimum noise fraction (MNF), independent component analysis (ICA), and principal component analysis (PCA), were studied. Then, RF was used to finely classify a variety of crops in hyperspectral images. The results showed: (1) The MNF–RF combination was the best ideal classification combination in this study. The best classification accuracies of the MNF–RF random sample set in the Longkou and Honghu areas were 97.18% and 80.43%, respectively; compared with the original image, the RF classification accuracy was improved by 6.43% and 8.81%, respectively. (2) For this study, the overall classification accuracy of RF in the two regions was positively correlated with the number of random sample points. (3) The image after feature transform was less affected by the number of sample points than the original image. The MNF transform curve of the overall RF classification accuracy in the two regions varied with the number of random sample points but was the smoothest and least affected by the number of sample points, followed by the PCA transform and ICA transform curves. The overall classification accuracies of MNF–RF in the Longkou and Honghu areas did not exceed 0.50% and 3.25%, respectively, with the fluctuation of the number of sample points. This research can provide reference for the fine classification of crops based on UAV-borne hyperspectral images. [ABSTRACT FROM AUTHOR]

Applications of machine-learning-based approaches in the geosciences have witnessed a substantial increase over the past few years. Here we present an approach that accounts for spatial autocorrelation by introducing spatial features to the models. In particular, we explore two types of spatial features, namely spatial lag and eigenvector spatial filtering (ESF). These features are used within the widely used random forest (RF) method, and their effect is illustrated on two public datasets of varying sizes (Meuse and California housing datasets). The least absolute shrinkage and selection operator (LASSO) is used to determine the best subset of spatial features, and nested cross-validation is used for hyper-parameter tuning and performance evaluation. We utilize Moran's I and local indicators of spatial association (LISA) to assess how spatial autocorrelation is captured at both global and local scales. Our results show that RF models combined with either spatial lag or ESF features yield lower errors (up to 33% different) and reduce the global spatial autocorrelation of the residuals (up to 95% decrease in Moran's I) compared to the RF model with no spatial features. The local autocorrelation patterns of the residuals are weakened as well. Compared to benchmark geographically weighted regression (GWR) models, the RF models with spatial features yielded more accurate models with similar levels of global and local autocorrelation in the prediction residuals. This study reveals the effectiveness of spatial features in capturing spatial autocorrelation and provides a generic machine-learning modelling workflow for spatial prediction. [ABSTRACT FROM AUTHOR]

Point cloud semantic segmentation has played an important role in the scan-to-BIM process of the Ming and Qing Dynasties' official-style architecture roof. To overcome the complexity of roof components' shape and the scale differences between different roof component types, a point cloud semantic segmentation method for the MQDOAs roof considering the construction regulations is proposed in this paper. This method is composed of two stages. In the first stage, the features from the construction rules of MQDOAs, including the normalized symmetrical distance (NSD), relative height (RH) and local height difference (LHD), are extracted alongside the regular geometric features. To lower the influence of scale differences, a multi-scale feature connection strategy is also applied to construct the feature classification vector. In the second stage, RF method is applied to classify the point cloud. To verify the efficiency of the proposed method, we took the Hall of Complete Harmony as the study case. The experiments showed that our method achieved segmentation result in overall classification accuracy and reached 96.8%. [ABSTRACT FROM AUTHOR]

This study predicts the presence or absence of terrorism in Europe on a previously unexplored spatial scale. Dependent variables consist of satellite imagery and socio-environmental data. Five machine learning models were evaluated over the following binary classification problem: the presence or absence of historical attacks within hexagonal-grid cells of 25 square kilometers. Four spatial statistics were conducted to assess the validity of the results and improve our inferential understanding of spatial processes among terror attacks. This analysis resulted in a Random Forest model that achieves 0.99 accuracy in predicting the presence or absence of terrorism at a spatial resolution of approximately 5 km. The results were validated by robust F1 and average precision scores of 0.96 and 0.97, respectively. Additionally, statistical analysis revealed spatial differences between separatists and all other terrorist types. This work concludes that remote sensing, machine learning, and spatial techniques are important and valuable methods for providing insight into terrorist activity and behavior. [ABSTRACT FROM AUTHOR]

As the convenient outlet to the Bo Sea and the major region of economic development in the Yellow River Basin, Shandong Province in China has undergone large changes in land use/land cover (LULC) in the past two decades with rapid urbanization and population growth. The analysis of the LULC change patterns and its driving factors in the Shandong section of the Yellow River Basin can provide a scientific basis for rational planning and ecological protection of land resources in the Shandong section of the Yellow River Basin. In this manuscript, we analyzed the spatial pattern of LULC and its spatial and temporal changes in the Shandong section of the Yellow River Basin in 2000, 2010, and 2020 by using the random forest classification algorithm with the Google Earth Engine platform and multi-temporal Landsat TM/OLI data. The driving factors of LULC changes were also quantified by the factor detector and interaction detector in the geodetector. Results show that in the past two decades, the LULC types in the study area are mainly farmland and construction land, among which the proportion of farmland area has decreased and the proportion of construction land area has increased from 19.4% to 29.7%. Based on the results of factor detector, it can be concluded that elevation, slope, and soil type are the key factors affecting LULC change in the study area. The interaction between elevation and slope, slope and soil type, and temperature and precipitation has strong explanatory power for the spatial variation of LULC change in the study area. The research results can provide data support for ecological environmental protection, sustainable, and high-quality development of the Shandong section of the Yellow River Basin, and help local governments take corresponding measures to achieve coordinated and sustainable socioeconomic and environmental development. [ABSTRACT FROM AUTHOR]

Map generalization utilizes transformation operations to derive smaller-scale maps from larger-scale maps and is a key procedure for the modelling and understanding of geographic space. Studies to date have largely applied a fixed tolerance to aggregate clustered buildings into a single object, resulting in the loss of details that meet cartographic constraints and may be of importance for users. This study aims to develop a method that amalgamates clustered buildings gradually without significant modification of geometry, while preserving the map details as much as possible under cartographic constraints. The amalgamation process consists of three key steps. First, individual buildings are grouped into distinct clusters by using the graph-based spatial clustering application with random forest (GSCARF) method. Second, building clusters are decomposed into scaling subgroups according to homogeneity with regard to the mean distance of subgroups. Thus, hierarchies of building clusters can be derived based on scaling subgroups. Finally, an amalgamation operation is progressively performed from the bottom-level subgroups to the top-level subgroups using the maximum distance of each subgroup as the amalgamating tolerance instead of using a fixed tolerance. As a consequence of this step, generalized intermediate scaling results are available, which can form the multi-scale representation of buildings. The experimental results show that the proposed method can generate amalgams with correct details, statistical area balance and orthogonal shape while satisfying cartographic constraints (e.g., minimum distance and minimum area). [ABSTRACT FROM AUTHOR]

The indoor location of individuals is a key contextual variable for commercial and assisted location-based services and applications. Commercial centers and medical buildings (e.g., hospitals) require location information of their users/patients to offer the services that are needed at the correct moment. Several approaches have been proposed to tackle this problem. In this paper, we present the development of an indoor location system which relies on the human activity recognition approach, using sound as an information source to infer the indoor location based on the contextual information of the activity that is realized at the moment. In this work, we analyze the sound information to estimate the location using the contextual information of the activity. A feature extraction approach to the sound signal is performed to feed a random forest algorithm in order to generate a model to estimate the location of the user. We evaluate the quality of the resulting model in terms of sensitivity and specificity for each location and we also perform out-of-bag error estimation. Our experiments were carried out in five representative residential homes. Each home had four individual indoor rooms. Eleven activities (brewing coffee, cooking, eggs, taking a shower, etc.) were performed to provide the contextual information. Experimental results show that developing an indoor location system (ILS) that uses contextual information from human activities (identified with data provided from the environmental sound) can achieve an estimation that is 95% correct. [ABSTRACT FROM AUTHOR]

This paper proposes the use of Stacked Random Forests (SRF) for the classification of Polarimetric Synthetic Aperture Radar images. SRF apply several Random Forest instances in a sequence where each individual uses the class estimate of its predecessor as an additional feature. To this aim, the internal node tests are designed to work not only directly on the complex-valued image data, but also on spatially varying probability distributions and thus allow a seamless integration of RFs within the stacking framework. Experimental results show that the classification performance is consistently improved by the proposed approach, i.e., the achieved accuracy is increased by 4% and 7% for one fully- and one dual-polarimetric dataset. This increase only comes at the cost of a linear increased training and prediction time, which is rather limited as the method converges quickly. [ABSTRACT FROM AUTHOR]

Naïve Geography, intelligent geographical information systems (GIS), and spatial data mining especially from social media all rely on natural-language spatial relations (NLSR) terms to incorporate commonsense spatial knowledge into conventional GIS and to enhance the semantic interoperability of spatial information in social media data. Yet, the inherent fuzziness of NLSR terms makes them challenging to interpret. This study proposes to interpret the fuzzy semantics of NLSR terms using the fuzzy random forest (FRF) algorithm. Based on a large number of fuzzy samples acquired by transforming a set of crisp samples with the random forest algorithm, two FRF models with different membership assembling strategies are trained to obtain the fuzzy interpretation of three line-region geometric representations using 69 NLSR terms. Experimental results demonstrate that the two FRF models achieve good accuracy in interpreting line-region geometric representations using fuzzy NLSR terms. In addition, fuzzy classification of FRF can interpret the fuzzy semantics of NLSR terms more fully than their crisp counterparts. [ABSTRACT FROM AUTHOR]

The objective of this research was to investigate the impact of seasonality on urban land-cover mapping and to explore better classification accuracy by using multi-season Sentinel-1A and GF-1 wide field view (WFV) images, and the combinations of both types of images in subtropical monsoon-climate regions in Southeast China. We obtained multi-season Sentinel-1A and GF-1 WFV images, as well as the combinations of both data, by using a support vector machine (SVM) and a random forest (RF) classifier. The backscatter intensity, texture, and interference-coherence images were extracted from Sentinel-1A images, and different combinations of these Sentinel-1A-derived images were used to evaluate their ability to map urban land cover. The results showed that the performance of winter images was better than that of any other season, while the summer images performed the worst. Higher classification accuracy was achieved by using multi-season images, and satisfactory classification results were obtained when using Sentinel-1A images from only three seasons. The best classification result was achieved using a combination of all Sentinel-1A data from all four seasons and GF-1 WFV data from winter, with an overall accuracy of up to 96.02% and a kappa coefficient reaching 0.9502. The performance of textures was slightly better than that of the backscatter-intensity images. Although the coherence data performed the worst, it was still able to distinguish urban impervious surfaces well. In addition, the overall classification accuracy of RF was better than that of SVM. [ABSTRACT FROM AUTHOR]

The Mw 7.8 Gorkha earthquake of 25 April 2015 triggered thousands of landslides in the central part of the Nepal Himalayas. The main goal of this study was to generate an ensemble-based map of co-seismic landslide susceptibility in Sindhupalchowk District using model comparison and combination strands. A total of 2194 co-seismic landslides were identified and were randomly split into 1536 (~70%), to train data for establishing the model, and the remaining 658 (~30%) for the validation of the model. Frequency ratio, evidential belief function, and weight of evidence methods were applied and compared using 11 different causative factors (peak ground acceleration, epicenter proximity, fault proximity, geology, elevation, slope, plan curvature, internal relief, drainage proximity, stream power index, and topographic wetness index) to prepare the landslide susceptibility map. An ensemble of random forest was then used to overcome the various prediction limitations of the individual models. The success rates and prediction capabilities were critically compared using the area under the curve (AUC) of the receiver operating characteristic curve (ROC). By synthesizing the results of the various models into a single score, the ensemble model improved accuracy and provided considerably more realistic prediction capacities (91%) than the frequency ratio (81.2%), evidential belief function (83.5%) methods, and weight of evidence (80.1%). [ABSTRACT FROM AUTHOR]

As an intermediate step between raw remote sensing data and digital maps, remote sensing data classification has been a challenging and long-standing problem in the remote sensing research community. In this work, an automated and effective supervised classification framework is presented for classifying high-resolution remote sensing data. Specifically, the presented method proceeds in three main stages: feature extraction, classification, and classified result refinement. In the feature extraction stage, both multispectral images and 3D geometry data are used, which utilizes the complementary information from multisource data. In the classification stage, to tackle the problems associated with too many training samples and take full advantage of the information in the large-scale dataset, a random forest (RF) ensemble learning strategy is proposed by combining several RF classifiers together. Finally, an improved fully connected conditional random field (FCCRF) graph model is employed to derive the contextual information to refine the classification results. Experiments on the ISPRS Semantic Labeling Contest dataset show that the presented 3-stage method achieves 86.9% overall accuracy, which is a new state-of-the-art non-CNN (convolutional neural networks)-based classification method. [ABSTRACT FROM AUTHOR]

The increased feature space available in object-based classification environments (e.g., extended spectral feature sets per object, shape properties, or textural features) has a high potential of improving classifications. However, the availability of a large number of derived features per segmented object can also lead to a time-consuming and subjective process of optimizing the feature subset. The objectives of this study are to evaluate the effect of the advanced feature selection methods of popular supervised classifiers (Support Vector Machines (SVM) and Random Forest (RF)) for the example of object-based mapping of an agricultural area using Unmanned Aerial Vehicle (UAV) imagery, in order to optimize their usage for object-based agriculture pattern recognition tasks. In this study, several advanced feature selection methods were divided into both types of classifiers (SVM and RF) to conduct further evaluations using five feature-importance-evaluation methods and three feature-subset-evaluation methods. A visualization method was used to measure the change pattern of mean classification accuracy with the increase of features used, and a two-tailed t-test was used to determine the difference between two population means for both repeated ten classification accuracies. This study mainly contribute to the uncertainty analysis of feature selection for object-based classification instead of the per-pixel method. The results highlight that the RF classifier is relatively insensitive to the number of input features, even for a small training set size, whereby a negative impact of feature set size on the classification accuracy of the SVM classifier was observed. Overall, the SVM Recursive Feature Elimination (SVM-RFE) seems to be an appropriate method for both groups of classifiers, while the Correlation-based Feature Selection (CFS) is the best feature-subset-evaluation method. Most importantly, this study verified that feature selection for both classifiers is crucial for the evolving field of Object-based Image Analysis (OBIA): It is highly advisable for feature selection to be performed before object-based classification, even though an adverse impact could sometimes be observed from the wrapper methods. [ABSTRACT FROM AUTHOR]

Sustainable urban planning and management require reliable land change models, which can be used to improve decision making. The objective of this study was to test a random forest-cellular automata (RF-CA) model, which combines random forest (RF) and cellular automata (CA) models. The Kappa simulation (KSimulation), figure of merit, and components of agreement and disagreement statistics were used to validate the RF-CA model. Furthermore, the RF-CA model was compared with support vector machine cellular automata (SVM-CA) and logistic regression cellular automata (LR-CA) models. Results show that the RF-CA model outperformed the SVM-CA and LR-CA models. The RF-CA model had a Kappa simulation (KSimulation) accuracy of 0.51 (with a figure of merit statistic of 47%), while SVM-CA and LR-CA models had a KSimulation accuracy of 0.39 and -0.22 (with figure of merit statistics of 39% and 6%), respectively. Generally, the RF-CA model was relatively accurate at allocating "non-built-up to built-up" changes as reflected by the correct "non-built-up to built-up" components of agreement of 15%. The performance of the RF-CA model was attributed to the relatively accurate RF transition potential maps. Therefore, this study highlights the potential of the RF-CA model for simulating urban growth. [ABSTRACT FROM AUTHOR]

One of the core tasks in digital soil mapping (DSM) studies is the estimation of the spatial distribution of different soil variables. In addition, however, assessing the uncertainty of these estimations is equally important, something that a lot of current DSM studies lack. Machine learning (ML) methods are increasingly used in this scientific field, the majority of which do not have intrinsic uncertainty estimation capabilities. A solution to this is the use of specific ML methods that provide advanced prediction capabilities, along with innate uncertainty estimation metrics, like Quantile Regression Forests (QRF). In the current paper, the prediction and the uncertainty capabilities of QRF, Random Forests (RF) and geostatistical methods were assessed. It was confirmed that QRF exhibited outstanding results at predicting soil organic matter (OM) in the study area. In particular, R2 was much higher than the geostatistical methods, signifying that more variation is explained by the specific model. Moreover, its uncertainty capabilities as presented in the uncertainty maps, shows that it can also provide a good estimation of the uncertainty with distinct representation of the local variation in specific parts of the area, something that is considered a significant advantage, especially for decision support purposes. [ABSTRACT FROM AUTHOR]

Satellite retrieval can offer global soil moisture information, such as Advanced Microwave Scanning Radiometer-Earth Observing System (AMSR-E) data. AMSR-E has been used to provide soil moisture all over the world, with a coarse resolution of 25 km × 25 km. The coarse resolution of the soil moisture dataset often hinders its use in local or regional research. This work proposes a new framework based on the random forest (RF) model while using five auxiliary data to downscale the AMSR-E soil moisture data over North China. The downscaled results with a 1 km spatial resolution are verified against in situ measurements. Compared with AMSR-E data, the correlation coefficient of the downscaled data is increased by 0.17, and the root mean squared error, mean absolute error, and unbiased root mean square error are reduced by 0.02, 0.01, and 0.03 m3/m3, respectively. In addition, the comparison results with Multiple Linear Regression and Support Vector Regression downscaled data show that the proposed method significantly outperforms the other two methods. The feasibility of our model is well supported by the importance analysis and leave-one-out analysis. Our study, which combines RF with spatiotemporal search algorithms and efficient auxiliary data, may provide insights into soil moisture downscaling in large areas with various surface characteristics and climatic conditions. [ABSTRACT FROM AUTHOR]

Following economic growth in the past three decades, rapid urbanization has caused many pronounced issues, such as spatial scarcity and cultural discontinuity, in Chinese historical and cultural cities. In order to better deal with the diversification of underground space resources, data and information, this study introduces a random forest algorithm and proposes a multi-layer information superposition method. According to the characteristics of different information, starting from qualitative and quantitative aspects, we explore the effective performance of the rational development of underground space resources. Taking Yangzhou City, China, as an example, this paper evaluates the suitability and calculates the development volume of urban underground space. The development capacity, potential value, and comprehensive quality of underground space resources are explored in an attempt to demonstrate the practicality and scientificity of the evaluation method for achieving the developmental goals of urban space reconstruction and historic preservation. On this basis, an underground space scale forecast is carried out to provide decision support for relevant planners, managers, and construction personnel that is conducive to the orderly development of urban space, alleviation of increasing human–land conflicts, and coordination of the protection and development of underground space resources in historical and cultural cities, ultimately promoting sustainable development of cities. [ABSTRACT FROM AUTHOR]