Geospatial data sharing is an inevitable requirement for scientific and technological innovation and economic and social development decisions in the era of big data. With the development of modern information technology, especially Web 2.0, a large number of geospatial data sharing websites (GDSW) have been developed on the Internet. GDSW is a point of access to geospatial data, which is able to provide a geospatial data inventory. How to precisely identify these data websites is the foundation and prerequisite of sharing and utilizing web geospatial data and is also the main challenge of data sharing at this stage. GDSW identification can be regarded as a binary website classification problem, which can be solved by the current popular machine learning method. However, the websites obtained from the Internet contain a large number of blogs, companies, institutions, etc. If GDSW is directly used as the sample data of machine learning, it will greatly affect the classification precision. For this reason, this paper proposes a method to precisely identify GDSW by combining multi-source semantic information and machine learning. Firstly, based on the keyword set, we used the Baidu search engine to find the websites that may be related to geospatial data in the open web environment. Then, we used the multi-source semantic information of geospatial data content, morphology, sources, and shared websites to filter out a large number of websites that contained geospatial keywords but were not related to geospatial data in the search results through the calculation of comprehensive similarity. Finally, the filtered geospatial data websites were used as the sample data of machine learning, and the GDSWs were identified and evaluated. In this paper, training sets are extracted from the original search data and the data filtered by multi-source semantics, the two datasets are trained by machine learning classification algorithms (KNN, LR, RF, and SVM), and the same test datasets are predicted. The results show that: (1) compared with the four classification algorithms, the classification precision of RF and SVM on the original data is higher than that of the other two algorithms. (2) Taking the data filtered by multi-source semantic information as the sample data for machine learning, the precision of all classification algorithms has been greatly improved. The SVM algorithm has the highest precision among the four classification algorithms. (3) In order to verify the robustness of this method, different initial sample data mentioned above are selected for classification using the same method. The results show that, among the four classification algorithms, the classification precision of SVM is still the highest, which shows that the proposed method is robust and scalable. Therefore, taking the data filtered by multi-source semantic information as the sample data to train through machine learning can effectively improve the classification precision of GDSW, and comparing the four classification algorithms, SVM has the best classification effect. In addition, this method has good robustness, which is of great significance to promote and facilitate the sharing and utilization of open geospatial data. Full article

The crack ratio is one of the indices used to quantitatively evaluate the soundness of asphalt pavement. However, since the inspection of pavement requires much labor and cost, automatic inspection of pavement damage by image analysis is required in order to reduce the burden of such work. In this study, a system was constructed that automatically detects and evaluates cracks from images of pavement using a convolutional neural network, a kind of deep learning. The most novel aspect of this study is that the accuracy was recursively improved through retraining the convolutional neural network (CNN) by collecting images which had previously been incorrectly analyzed. Then, study and implementation were conducted of a system for plotting the results in a GIS. In addition, an experiment was carried out applying this system to images actually taken from an MMS (mobile mapping system), and this confirmed that the system had high crack evaluation performance. Full article

The Vector Assignment Ordered Median Problem (VAOMP) is a new unified approach for location-allocation problems, which are one of the most important forms of applied analysis in GIS (Geospatial Information System). Solving location-allocation problems with exact methods is difficult and time-consuming, especially when the number of objectives and criteria increases. One of the most important criteria in location-allocation problems is the capacity of facilities. Firstly, this study develops a new VAOMP approach by including capacity as a criterion, resulting in a new model known as VAOCMP (Vector Assignment Ordered Capacitated Median Problem). Then secondly, the results of applying VAOMP, in scenario 1, and VAOCMP, in scenario 2, for the location-allocation of fire stations in Tehran, with the objective of minimizing the arrival time of fire engines to an incident site to no more than 5 min, are examined using both the Tabu Search and Simulated Annealing algorithms in GIS. The results of scenario 1 show that 52,840 demands were unable to be served with 10 existing stations. In scenario 2, given that each facility could not accept demand above its capacity, the number of demands without service increased to 59,080, revealing that the number of stations in the study area is insufficient. Adding 35 candidate stations and performing relocation-reallocation revealed that at least three other stations are needed for optimal service. Thirdly, and finally, the VAOMP and VAOCMP were implemented in a modest size problem. The implementation results for both algorithms showed that the Tabu Search algorithm performed more effectively. Full article

In recent years, the incidence of localized heavy rainfall has increased as abnormal weather events occur more frequently. In densely populated urban areas, this type of heavy rain can cause extreme landslide damage, so that it is necessary to estimate and analyze the susceptibility of future landslides. In this regard, deep learning (DL) methodologies have been used to identify areas prone to landslides recently. Therefore, in this study, DL methodologies, including a deep neural network (DNN), kernel-based DNN, and convolutional neural network (CNN) were used to identify areas where landslides could occur. As a detailed step for this purpose, landslide occurrence was first determined as landslide inventory through aerial photographs with comparative analysis using field survey data; a training set was built for model training through oversampling based on the landslide inventory. A total of 17 landslide influencing variables that influence the frequency of landslides by topography and geomorphology, as well as soil and forest variables, were selected to establish a landslide inventory. Then models were built using DNN, kernel-based DNN, and CNN models, and the susceptibility of landslides in the study area was determined. Model performance was evaluated through the average precision (AP) score and root mean square error (RMSE) for each of the three models. Finally, DNN, kernel-based DNN, and CNN models showed performances of 99.45%, 99.44%, and 99.41%, and RMSE values of 0.1694, 0.1806, and 0.1747, respectively. As a result, all three models showed similar performance, indicating excellent predictive ability of the models developed in this study. The information of landslides occurring in urban areas, which cause a great damage even with a small number of occurrences, can provide a basis for reference to the government and local authorities for urban landslide management. Full article

Case-based reasoning (CBR) systems often provide a basis for decision makers to make management decisions in disaster prevention and emergency response. For decades, many CBR systems have been implemented by using expert knowledge schemes to build indexes for case identification from a case library of situations and to explore the relations among cases. However, a knowledge elicitation bottleneck occurs for many knowledge-based CBR applications because expert reasoning is difficult to precisely explain. To solve these problems, this paper proposes a method using only knowledge to recognize marine oil spill cases. The proposed method combines deep reinforcement learning (DRL) with strategy selection to determine emergency responses for marine oil spill accidents by quantification of the marine oil spill scenario as the reward for the DRL agent. These accidents are described by scenarios and are considered the state inputs in the hybrid DRL/CBR framework. The challenges and opportunities of the proposed method are discussed considering different scenarios and the intentions of decision makers. This approach may be helpful in terms of developing hybrid DRL/CBR-based tools for marine oil spill emergency response. Full article

This paper aims to apply and compare the performance of the three machine learning algorithms–support vector machine (SVM), bayesian logistic regression (BLR), and alternating decision tree (ADTree)–to map landslide susceptibility along the mountainous road of the Salavat Abad saddle, Kurdistan province, Iran. We identified 66 shallow landslide locations, based on field surveys, by recording the locations of the landslides by a global position System (GPS), Google Earth imagery and black-and-white aerial photographs (scale 1: 20,000) and 19 landslide conditioning factors, then tested these factors using the information gain ratio (IGR) technique. We checked the validity of the models using statistical metrics, including sensitivity, specificity, accuracy, kappa, root mean square error (RMSE), and area under the receiver operating characteristic curve (AUC). We found that, although all three machine learning algorithms yielded excellent performance, the SVM algorithm (AUC = 0.984) slightly outperformed the BLR (AUC = 0.980), and ADTree (AUC = 0.977) algorithms. We observed that not only all three algorithms are useful and effective tools for identifying shallow landslide-prone areas but also the BLR algorithm can be used such as the SVM algorithm as a soft computing benchmark algorithm to check the performance of the models in future. Full article

Droughts can cause significant damage to agriculture and water resources, leading to severe economic losses and loss of life. One of the most important aspect is to develop effective tools to forecast drought events that could be helpful in mitigation strategies. The understanding of droughts has become more challenging because of the effect of climate change, urbanization and water management; therefore, the present study aims to forecast droughts by determining an appropriate index and analyzing its changes, using climate variables. The work was conducted in three different phases, first being the determination of Standard Precipitation Evaporation Index (SPEI), using global climatic dataset of Climate Research Unit (CRU) from 1901–2018. The indices are calculated at different monthly intervals which could depict short-term or long-term changes, and the index value represents different drought classes, ranging from extremely dry to extremely wet. However, the present study was focused only on forecasting at short-term scales for New South Wales (NSW) region of Australia and was conducted at two different time scales, one month and three months. The second phase involved dividing the data into three sample sizes, training (1901–2010), testing (2011–2015) and validation (2016–2018). Finally, a machine learning approach, Random Forest (RF), was used to train and test the data, using various climatic variables, e.g., rainfall, potential evapotranspiration, cloud cover, vapor pressure and temperature (maximum, minimum and mean). The final phase was to analyze the performance of the model based on statistical metrics and drought classes. Regarding this, the performance of the testing period was conducted by using statistical metrics, Coefficient of Determination (R²) and Root-Mean-Square-Error (RMSE) method. The performance of the model showed a considerably higher value of R² for both the time scales. However, statistical metrics analyzes the variation between the predicted and observed index values, and it does not consider the drought classes. Therefore, the variation in predicted and observed SPEI values were analyzed based on different drought classes, which were validated by using the Receiver Operating Characteristic (ROC)-based Area under the Curve (AUC) approach. The results reveal that the classification of drought classes during the validation period had an AUC of 0.82 for SPEI 1 case and 0.84 for SPEI 3 case. The study depicts that the Random Forest model can perform both regression and classification analysis for drought studies in NSW. The work also suggests that the performance of any model for drought forecasting should not be limited only through statistical metrics, but also by examining the variation in terms of drought characteristics. Full article

This paper describes the development of an optimized corn yield prediction model under extreme weather conditions for the Midwestern United States (US). We tested six different artificial intelligence (AI) models using satellite images and meteorological data for the dominant growth period. To examine the effects of extreme weather events, we defined the drought and heatwave by considering the characteristics of corn growth and selected the cases for sensitivity tests from a historical database. In particular, we conducted an optimization for the hyperparameters of the deep neural network (DNN) model to ensure the best configuration for accuracy improvement. The result for drought cases showed that our DNN model was approximately 51–98% more accurate than the other five AI models in terms of root mean square error (RMSE). For the heatwave cases, our DNN model showed approximately 30–77% better accuracy in terms of RMSE. The correlation coefficient was 0.954 for drought cases and 0.887–0.914 for heatwave cases. Moreover, the accuracy of our DNN model was very stable, despite the increases in the duration of the heatwave. It indicates that the optimized DNN model can provide robust predictions for corn yield under conditions of extreme weather and can be extended to other prediction models for various crops in future work. Full article

Landslides are known as the world’s most dangerous threat in mountainous regions and pose a critical obstacle for both economic and infrastructural progress. It is, therefore, quite relevant to discuss the pattern of spatial incidence of this phenomenon. The current research manifests a set of individual and ensemble of machine learning and probabilistic approaches like an artificial neural network (ANN), support vector machine (SVM), random forest (RF), logistic regression (LR), and their ensembles such as ANN-RF, ANN-SVM, SVM-RF, SVM-LR, LR-RF, LR-ANN, ANN-LR-RF, ANN-RF-SVM, ANN-SVM-LR, RF-SVM-LR, and ANN-RF-SVM-LR for mapping landslide susceptibility in Rudraprayag district of Garhwal Himalaya, India. A landslide inventory map along with sixteen landslide conditioning factors (LCFs) was used. Randomly partitioned sets of 70%:30% were used to ascertain the goodness of fit and predictive ability of the models. The contribution of LCFs was analyzed using the RF model. The altitude and drainage density were found to be the responsible factors in causing the landslide in the study area according to the RF model. The robustness of models was assessed through three threshold dependent measures, i.e., receiver operating characteristic (ROC), precision and accuracy, and two threshold independent measures, i.e., mean-absolute-error (MAE) and root-mean-square-error (RMSE). Finally, using the compound factor (CF) method, the models were prioritized based on the results of the validation methods to choose best model. Results show that ANN-RF-LR indicated a realistic finding, concentrating only on 17.74% of the study area as highly susceptible to landslide. The ANN-RF-LR ensemble demonstrated the highest goodness of fit and predictive capacity with respective values of 87.83% (area under the success rate curve) and 93.98% (area under prediction rate curve), and the highest robustness correspondingly. These attempts will play a significant role in ensemble modeling, in building reliable and comprehensive models. The proposed ANN-RF-LR ensemble model may be used in the other geographic areas having similar geo-environmental conditions. It may also be used in other types of geo-hazard modeling. Full article

Radiometric normalization is an essential preprocessing step that must be performed to detect changes in multi-temporal satellite images and, in general, relative radiometric normalization is utilized. However, most relative radiometric normalization methods assume a linear relationship and they cannot take into account nonlinear properties, such as the distribution of the earth’s surface or phenological differences that are caused by the growth of vegetation. Thus, this paper proposes a novel method that assumes a nonlinear relationship and it uses a representative nonlinear regression model—multilayer perceptron (MLP). The proposed method performs radiometric resolution compression while considering both the complexity and time cost, and radiometric control set samples are extracted based on a no-change set method. Subsequently, the spectral index is selected for each band to compensate for the phenological properties, phenological normalization is performed based on MLP, and the global radiometric properties are adjusted through postprocessing. Finally, a performance evaluation is conducted by comparing the results herein with those from conventional relative radiometric normalization algorithms. The experimental results show that the proposed method outperforms conventional methods in terms of both visual inspection and quantitative evaluation. In other words, the applicability of the proposed method to the normalization of multi-temporal images with nonlinear properties is confirmed. Full article

Research on clouds has an enormous influence on sky sciences and related applications, and cloud classification plays an essential role in it. Much research has been conducted which includes both traditional machine learning approaches and deep learning approaches. Compared with traditional machine learning approaches, deep learning approaches achieved better results. However, most deep learning models need large data to train due to the large number of parameters. Therefore, they cannot get high accuracy in case of small datasets. In this paper, we propose a complete solution for high accuracy of classification of cloud image patches on small datasets. Firstly, we designed a suitable convolutional neural network (CNN) model for small datasets. Secondly, we applied regularization techniques to increase generalization and avoid overfitting of the model. Finally, we introduce a model average ensemble to reduce the variance of prediction and increase the classification accuracy. We experiment the proposed solution on the Singapore whole-sky imaging categories (SWIMCAT) dataset, which demonstrates perfect classification accuracy for most classes and confirms the robustness of the proposed model. Full article

Since it is not possible to determine the exact time of a natural disaster’s occurrence and the amount of physical and financial damage on humans or the environment resulting from their event, decision-makers need to identify areas with potential vulnerability in order to reduce future losses. In this paper, a GIS-based open source software entitled Seismic-Related Vulnerability Calculation Software (SEVUCAS), based on the Step-wise Weight Assessment Ratio Analysis (SWARA) method and geographic information system, has been developed to assess seismic vulnerability by considering four groups of criteria (i.e., geotechnical, structural, socio-economic, and physical distance to needed facilities and away from dangerous facilities). The software was developed in C# language using ArcGIS Engine functions, which provide enhanced visualization as well as user-friendly and automatic software for the seismic vulnerability assessment of buildings. Weighting of the criteria (indicators) and alternatives (sub-indicators) was done using SWARA. Also, two interpolation methods based on a radial basis function (RBF) and teaching–learning-based optimization (TLBO) were used to optimize the weights of the criteria and the classes of each alternative as well. After weighing the criteria and alternatives, the weighted overlay analysis was used to determine the final vulnerability map in the form of contours and statistical data. The difference between this software and similar ones is that people with a low level of knowledge in the area of earthquake crisis management can use it to determine and estimate the seismic vulnerabilities of their houses. This visualized operational forecasting software provides an applicable tool for both government and people to make quick and correct decisions to determine higher priority structures for seismic retrofitting implementation. Full article

Data security technology is of great significance for the effective use of high-resolution remote sensing (HRRS) images in GIS field. Integrity authentication technology is an important technology to ensure the security of HRRS images. Traditional authentication technologies perform binary level authentication of the data and cannot meet the authentication requirements for HRRS images, while perceptual hashing can achieve perceptual content-based authentication. Compared with traditional algorithms, the existing edge-feature-based perceptual hash algorithms have already achieved high tampering authentication accuracy for the authentication of HRRS images. However, because of the traditional feature extraction methods they adopt, they lack autonomous learning ability, and their robustness still exists and needs to be improved. In this paper, we propose an improved perceptual hash scheme based on deep learning (DL) for the authentication of HRRS images. The proposed method consists of a modified U-net model to extract robust feature and a principal component analysis (PCA)-based encoder to generate perceptual hash values for HRRS images. In the training stage, a training sample generation method combining artificial processing and Canny operator is proposed to generate robust edge features samples. Moreover, to improve the performance of the network, exponential linear unit (ELU) and batch normalization (BN) are applied to extract more robust and accurate edge feature. The experiments have shown that the proposed algorithm has almost 100% robustness to format conversion between TIFF and BMP, LSB watermark embedding and lossless compression. Compared with the existing algorithms, the robustness of the proposed algorithm to lossy compression has been improved, with an average increase of 10%. What is more, the algorithm has good sensitivity to detect local subtle tampering to meet the high-accuracy requirements of authentication for HRRS images. Full article

Using satellite remote sensing has become a mainstream approach for extracting crop spatial distribution. Making edges finer is a challenge, while simultaneously extracting crop spatial distribution information from high-resolution remote sensing images using a convolutional neural network (CNN). Based on the characteristics of the crop area in the Gaofen 2 (GF-2) images, this paper proposes an improved CNN to extract fine crop areas. The CNN comprises a feature extractor and a classifier. The feature extractor employs a spectral feature extraction unit to generate spectral features, and five coding-decoding-pair units to generate five level features. A linear model is used to fuse features of different levels, and the fusion results are up-sampled to obtain a feature map consistent with the structure of the input image. This feature map is used by the classifier to perform pixel-by-pixel classification. In this study, the SegNet and RefineNet models and 21 GF-2 images of Feicheng County, Shandong Province, China, were chosen for comparison experiment. Our approach had an accuracy of 93.26%, which is higher than those of the existing SegNet (78.12%) and RefineNet (86.54%) models. This demonstrates the superiority of the proposed method in extracting crop spatial distribution information from GF-2 remote sensing images. Full article

Extreme rainstorms have important socioeconomic consequences, but understanding their fine spatial structures and temporal evolution still remains challenging. In order to achieve this, in view of an evolutionary property of rainstorms, this paper designs a process-oriented algorithm for identifying and tracking rainstorms, named PoAIR. PoAIR uses time-series of raster datasets and consists of three steps. The first step combines an accumulated rainfall time-series and spatial connectivity to identify rainstorm objects at each time snapshot. Secondly, PoAIR adopts the geometrical features of eccentricity, rectangularity, roundness, and shape index, as well as the thematic feature of the mean rainstorm intensity, to match the same rainstorm objects in successive snapshots, and then tracks the same rainstorm objects during a rainstorm evolution sequence. In the third step, an evolutionary property of a rainstorm sequence is used to extrapolate its spatial location and geometrical features at the next time snapshot and reconstructs a rainstorm process by linking rainstorm sequences with an area-overlapping threshold. Experiments on simulated datasets demonstrate that PoAIR performs better than the Thunderstorm Identification, Tracking, Analysis and Nowcasting algorithm (TITAN) in both rainfall tracking and identifying the splitting, merging, and merging-splitting of rainstorm objects. Additionally, applications of PoAIR to Integrated Multi-satellitE Retrievals for Global Precipitation Mission (GPM/IMERG) final products covering mainland China show that PoAIR can effectively track rainstorm objects. Full article