Search

The classification of very high-resolution satellite imagery remains a focal point in remote sensing, attracting increased attention across diverse scientific disciplines. Various classification methods, including pixel- and object-based techniques, have been proposed, and their performances and limitations have been discussed in the literature. This paper presents a hybrid method that combines the strengths of pixel- and object-based methods in image classification to minimize errors associated with the segmentation process, particularly under-segmentation errors in object-based image analysis. The core concept behind the method lies in categorizing segmented image objects as either homogeneous or heterogeneous based on their class probability. In this process, the estimated possibilities from the object-based classification model are considered, and segments are designated as homogeneous or heterogeneous using a user-defined threshold. The object-based classification model determines the class labels for homogeneous image objects, while the heterogeneous ones, containing pixels representing different land cover classes, are classified using the pixel-based model. The performance of hybrid classification models, created by varying thresholds, is analysed using high-resolution WorldView-3 and WorldView-2 imagery and compared with pixel- and object-based classification results. For the implementation of image classification methods, Canonical Correlation Forest (CCF), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost) were employed. The findings indicated that employing the suggested hybrid strategy with a threshold value selected within a specific range (e.g. between 60% and 80%) and employing a robust classification algorithm that provides class probabilities (e.g. CCF) results in a statistically significant improvement in overall accuracy compared to pixel and object-based methods, with gains of 5% and 4%, respectively. Visual analysis of the produced thematic maps revealed that the proposed method minimizes the salt-and-pepper effect associated with pixel-based classification while mitigating segmentation problems arising from object-based classification. [ABSTRACT FROM AUTHOR]

Abstract Monitoring burned areas in Thailand and other tropical countries during the post-harvest season is becoming increasingly important. High-resolution remote sensing data from Sentinel-2 satellites, which have a short revisit time, is ideal for accurately and efficiently mapping burned regions. However, automating the mapping of agriculture residual on a national scale is challenging due to the volume of information and level of detail involved. In this study, a Sentinel-2A Level-1C Multispectral Instrument image (MSI) from February 27, 2018 was combined with object-based image analysis (OBIA) algorithms to identify burned areas in Mae Chaem, Chom Thong, Hod, Mae Sariang, and Mae La Noi Districts in Chiang Mai, Thailand. OBIA techniques were used to classify forest, agricultural, water bodies, newly burned, and old burned regions. The segmentation scale parameter value of 50 was obtained using only the original Sentinel-2A band in red, green, blue, near infrared (NIR), and Normalized Difference Vegetation Index (NDVI). The accuracy of the produced maps was assessed using an existing burned area dataset, and the burned area identified through OBIA was found to be 85.2% accurate compared to 500 random burned points from the dataset. These results suggest that the combination of OBIA and Sentinel-2A with a 10 m spatial resolution is very effective and promising for the process of burned area mapping.

Monitoring burned areas in Thailand and other tropical countries during the post-harvest season is becoming increasingly important. High-resolution remote sensing data from Sentinel-2 satellites, which have a short revisit time, is ideal for accurately and efficiently mapping burned regions. However, automating the mapping of agriculture residual on a national scale is challenging due to the volume of information and level of detail involved. In this study, a Sentinel-2A Level-1C Multispectral Instrument image (MSI) from February 27, 2018 was combined with object-based image analysis (OBIA) algorithms to identify burned areas in Mae Chaem, Chom Thong, Hod, Mae Sariang, and Mae La Noi Districts in Chiang Mai, Thailand. OBIA techniques were used to classify forest, agricultural, water bodies, newly burned, and old burned regions. The segmentation scale parameter value of 50 was obtained using only the original Sentinel-2A band in red, green, blue, near infrared (NIR), and Normalized Difference Vegetation Index (NDVI). The accuracy of the produced maps was assessed using an existing burned area dataset, and the burned area identified through OBIA was found to be 85.2% accurate compared to 500 random burned points from the dataset. These results suggest that the combination of OBIA and Sentinel-2A with a 10 m spatial resolution is very effective and promising for the process of burned area mapping. [ABSTRACT FROM AUTHOR]

Riparian habitats are the most crucial yet the most fragile ecosystems, focal to safeguarding both the aquatic and terrestrial regions. Technology such as remote sensing, now powered by cloud-based server-side processing of high-resolution satellite imagery, and Big Data analytics, such as Google Earth Engine (GEE) combined with uncrewed aerial vehicles (UAVs), have accentuated ecological monitoring of natural habitats. This study leverages a nested approach to remote sensing, combining satellite data and UAV imagery to evaluate the present condition of riparian habitats along the Ganga River in the Upper Gangetic Plains. We used GEE to analyze Sentinel data and identify critical habitats, encompassing wetlands, grasslands, scrublands, plantations, river islands, and riparian forests in the study area. Strategic locations covering 291 km2 area were delineated, and over 1000 patches of 1 ha were isolated, with the largest patch of 23.99 km2 in Haiderpur. Furthermore, UAV-based data were collected for key identified regions. The status of a total of 284 field surveyed points was categorized as 29 intact grassland patches, 87 good habitat patches, 25 patches recently converted to agriculture, and 60 patches being converted to agriculture, remaining plantations, and waterbodies. UAV-based raster thematic maps of four key habitat regions generated using object-based image analysis classification found a promising approach for high-precision riparian habitat mapping, monitoring, and management, offering data quality, cost optimization, and time savings with an overall accuracy of 98% and kappa coefficient 0.97. UAV are, thus, effective tools for reach-level assessment of freshwater habitats, especially of smaller stream networks, retaining fine-scale riverscape information of the mosaic of land use and vegetation types.

Satellite data are essential during wildfires for understanding its adverse effects and improving the effectiveness of rapid disaster management. However, existing techniques used for damage assessments are inaccurate and lack automation. In this study, we propose an integrated machine learning approach with auto-generated training samples for a rapid wildfire disaster response framework using Sentinel-2 imagery at 10 m resolution from Google Earth Engine (GEE). First, training samples of burned areas were obtained by utilizing textural data based on features that had changed because of the wildfire, and samples of unburned areas were obtained using the normalized difference vegetation index (NDVI). The images were categorized as burned and unburned images using the object-based image analysis (OBIA) classification method. Finally, using the classified maps, burn severity maps and estimated pixel counts for each severity class were generated and compared. The proposed method was implemented to put out a wildfire that broke out in Uljin, Gyeongsangbuk-do, South Korea in March 2022 and the transferability of the model was evaluated in Gangneung, Gangwon-do, South Korea. The study findings indicate that the random forest (RF) classifier acquired the greatest overall accuracy (OA) of 97.6 % in Uljin; additionally, the model transferability performed well in Gangneung with an OA of 93.8 %. The RF also generated the fewest pixels of the unchanged class when the burn severity map was evaluated. Overall, our study proposes a quick and automated approach for estimating wildfire damage that could be used for immediate mitigation actions.

En el presente estudio se examinó el rendimiento de los algoritmos Support Vector Machine (SVM) y Random Forest (RF) utilizando un modelo de segmentación de imágenes basado en objetos (OBIA) en la zona metropolitana de Barranquilla, Colombia. El propósito fue investigar de qué manera los cambios en el tamaño de los conjuntos de entrenamiento y el desequilibrio en las clases de cobertura terrestre influyen en la precisión de los modelos clasificadores. Los valores del coeficiente Kappa y la precisión general revelaron que svm superó consistentemente a RF. Además, la imposibilidad de calibrar ciertos parámetros de SVM en ArcGIS Pro planteó desafíos. La elección del número de árboles en RF mostró ser fundamental, con un número limitado de árboles (50) que afectó la adaptabilidad del modelo, especialmente en conjuntos de datos desequilibrados. Este estudio resalta la complejidad de elegir y configurar modelos de aprendizaje automático, que acentúan la importancia de considerar cuidadosamente las proporciones de clases y la homogeneidad en las distribuciones de datos para lograr predicciones precisas en la clasificación de uso del suelo y cobertura terrestre. Según los hallazgos, alcanzar precisiones de usuario superiores al 90 % en las clases de pastos limpios, bosques, red vial y agua continental, mediante el modelo svm en ArcGIS Pro, requiere asignar muestras de entrenamiento que cubran respectivamente el 2 %, 1 %, 3 % y 8 % del área clasificada.

Copyright of Ciencia e Ingenieria Neogranadina is the property of Ciencia e Ingenieria Neogranadina and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Abstract Road network detection is critical to enhance disaster response and detecting a safe evacuation route. Due to expanding computational capacity, road extraction from aerial imagery has been investigated extensively in the literature, specifically in the last decade. Previous studies have mainly proposed methods based on pixel classification or image segmentation as road/non-road images, such as thresholding, edge-based segmentation, k-means clustering, histogram-based segmentation, etc. However, these methods have limitations of over-segmentation, sensitivity to noise, and distortion in images. This study considers the case study of Hawkesbury Nepean valley, NSW, Australia, which is prone to flood and has been selected for road network extraction. For road area extraction, the application of semantic segmentation along with residual learning and U-Net is suggested. Public road datasets were used for training and testing purposes. The study suggested a framework to train and test datasets with the application of the deep ResUnet architecture. Based on maximal similarity, the regions were merged, and the road network was extracted with the B-snake algorithm application. The proposed framework (baseline + region merging + B-snake) improved performance when evaluated on the synthetically modified dataset. It was evident that in comparison with the baseline, region merging and addition of the B-snake algorithm improved significantly, achieving a value of 0.92 for precision and 0.897 for recall.

Fostering urban resilience and adaptation to climate change pose new demands on the knowledge of land use and land cover (LULC) in heterogeneous urban spaces. High-resolution urban mapping is a valuable tool, which serves to map detailed categories. Such semantic data are integrated in national and regional administration as public goods. In the light of many countries around the globe making their data publicly available, we present a method to map urban areas based on multitemporal orthophotos and LiDAR-derived digital surface model, and extract information about vegetation in an automated processing chain. This approach is threshold driven and relies on an automatic generation of spectral thresholds and existing real-world-based classifications. We included cadastral data to add land-use information for specific categories, such as agricultural land use and to assess the product's accuracy. Adding these data creates an LULC product and makes a seamless integration into urban planning routines possible. The results of the study provide a detailed LULC map for the municipality of Aarhus in 2015 with a spatial resolution of 20 cm and ten thematic classes. Depending on the reference data, we achieved thematic overall accuracies of 34% and 64% using a polygon-based approach. Our study has found that utilizing both multitemporal orthophotos and elevation data can enhance the LC mapping of urban landscapes. The methodology could be transferred to other areas in Denmark or to countries providing similar datasets, and lends itself to a repeatable LULC mapping with minimal user interaction.

Accurate crop distribution mapping is required for crop yield prediction and field management. Due to rapid progress in remote sensing technology, fine spatial resolution (FSR) remotely sensed imagery now offers great opportunities for mapping crop types in great detail. However, within-class variance can hamper attempts to discriminate crop classes at fine resolutions. Multi-temporal FSR remotely sensed imagery provides a means of increasing crop classification from FSR imagery, although current methods do not exploit the available information fully. In this research, a novel Temporal Sequence Object-based Convolutional Neural Network (TS-OCNN) was proposed to classify agricultural crop type from FSR image time-series. An object-based CNN (OCNN) model was adopted in the TS-OCNN to classify images at the object level (i.e., segmented objects or crop parcels), thus, maintaining the precise boundary information of crop parcels. The combination of image time-series was first utilized as the input to the OCNN model to produce an ‘original’ or baseline classification. Then the single-date images were fed automatically into the deep learning model scene-by-scene in order of image acquisition date to increase successively the crop classification accuracy. By doing so, the joint information in the FSR multi-temporal observations and the unique individual information from the single-date images were exploited comprehensively for crop classification. The effectiveness of the proposed approach was investigated using multitemporal SAR and optical imagery, respectively, over two heterogeneous agricultural areas. The experimental results demonstrated that the newly proposed TS-OCNN approach consistently increased crop classification accuracy, and achieved the greatest accuracies (82.68% and 87.40%) in comparison with state-of-the-art benchmark methods, including the object-based CNN (OCNN) (81.63% and 85.88%), object-based image analysis (OBIA) (78.21% and 84.83%), and standard pixel-wise CNN (79.18% and 82.90%). The proposed approach is the first known attempt to explore simultaneously the joint information from image time-series with the unique information from single-date images for crop classification using a deep learning framework. The TS-OCNN, therefore, represents a new approach for agricultural landscape classification from multi-temporal FSR imagery. Besides, it is readily generalizable to other landscapes (e.g., forest landscapes), with a wide application prospect.

Submersed aquatic vegetation (SAV) plays an important role in ecosystems. Inventories of SAV spatial distribution and composition are important for monitoring changes in SAV. In this study, we compared three common SAV sampling methods to quantify SAV in western Lake Erie. Aerial imagery of near-shore areas in western Lake Erie was classified using object-based image analysis (OBIA) and evaluated against field-based surveys using single-beam sonar or rake samples. To assess variation among methods, data were assigned either vegetation 'presence' or 'absence' and compared for simple correspondence and agreement (Cohen's Kappa, κ). The two field-based methods had the highest correspondence at 78% (n = 782) and the highest κ = 0.545. Correspondence between OBIA and rake surveys was 69% (n = 245) and κ = 0.36. Correspondence between OBIA and hydroacoustics was the lowest of 54% (n = 30,768) with an agreement of κ = 0.17. Environmental factors such as water turbidity may have played a role in reduced agreement between OBIA and field methods. Determining the optimal method or combination of methods will depend upon research goals, effort, and cost, but each method can provide reliable SAV information for resource management. [ABSTRACT FROM AUTHOR]

Accurate assessment of Trees outside forest (TOF) is an essential input for the management and preservation of these vast resources, due to their importance in carbon sequestration and biodiversity conservation. Many studies have demonstrated the use of High-resolution satellite (HRS) imageries for mapping and monitoring of TOF in urban and rural landscapes. The conventional per-pixel classifier is not a suitable option for HRS data classification, owing to inherent high intra-class variability and high interclass similarity. In the present study, a convolution neural network-based approach was employed for TOF mapping using HRS images, predominantly in the urban landscape of Bengaluru city, India. We developed a semi-automated procedure for the generation of labelled training samples using object-based image analysis (OBIA), minimizing time requirement for input training data preparation for deep learning (DL) model development. These inputs were utilized to develop a DL model for the classification of TOF using U-Net, which is a semantic segmentation-based DL architecture. The results indicated that the model performed well for the classification of urban TOF with an overall classification accuracy of 89.65 percent and an F1 score of 93.03 percent, in comparison with OBIA (overall accuracy of 80.73 percent & F1 score of 86.44 percent). We demonstrated utilisation of a developed methodology for the assessment of TOF in a distinctive urban landscape, which can be extended to agriculture dominated regions in diverse landscapes. [ABSTRACT FROM AUTHOR]

Evaluating glacial change and the subsequent water stores in high mountains is becoming increasingly necessary, and in order to do this, models need reliable and consistent glacier data. These often come from global inventories, usually constructed from multi-temporal satellite imagery. However, there are limitations to these datasets. While clean ice can be mapped relatively easily using spectral band ratios, mapping debris-covered ice is more difficult due to the spectral similarity of supraglacial debris to the surrounding terrain. Therefore, analysts often employ manual delineation, a time-consuming and subjective approach to map debris-covered ice extents. Given the increasing prevalence of supraglacial debris in high mountain regions, such as High Mountain Asia, a systematic, objective approach is needed. The current study presents an approach for mapping debris-covered glaciers that integrates a convolutional neural network and object-based image analysis into one seamless classification workflow, applied to freely available and globally applicable Sentinel-2 multispectral, Landsat-8 thermal, Sentinel-1 interferometric coherence, and geomorphometric datasets. The approach is applied to three different domains in the Central Himalayan and the Karakoram ranges of High Mountain Asia that exhibit varying climatic regimes, topographies and debris-covered glacier characteristics. We evaluate the performance of the approach by comparison with a manually delineated glacier inventory, achieving F-score classification accuracies of 89.2%–93.7%. We also tested the performance of this approach on declassified panchromatic 1970 Corona KH-4B satellite imagery in the Manaslu region of Nepal, yielding accuracies of up to 88.4%. We find our approach to be robust, transferable to other regions, and accurate over regional (>4,000 km2) scales. Integrating object-based image analysis with deep-learning within a single workflow overcomes shortcomings associated with convolutional neural network classifications and permits a more flexible and robust approach for mapping debris-covered glaciers. The novel automated processing of panchromatic historical imagery, such as Corona KH-4B, opens the possibility of exploiting a wealth of multi-temporal data to understand past glacier changes.

The timely detection and mapping of surface water bodies from Polarimetric Synthetic Aperture Radar (PolSAR) images are of great significance for emergency management and post-disaster restoration tasks. Though various methods have been proposed in previous years, there are still some inherent flaws. Thus, this paper proposes a new surface water extraction method based on superpixels and Graph Convolutional Networks (GCN). First, the PolSAR images are segmented to generate superpixels as the basic unit of classification, and the graph structure data are established according to their connection to superpixels. Then, the features of each superpixel are extracted. Finally, a GCN is used to classify each superpixel unit using node features and their relationships. This study conducted experiments on a sudden flooding event due to heavy rain and a lake in the city. Detailed verification was carried out. Compared to traditional methods, the recall was improved by 3% while maintaining almost 100% accuracy in complex flood areas. The results show that the proposed method of surface water extraction from PolSAR images has great advantages, acquiring higher accuracy and better boundary adherence in cases of fewer samples. This paper also illustrates the advantage of using GCN to mine the contextual information of classification objects. [ABSTRACT FROM AUTHOR]

Plastic-covered greenhouse (PCG) segmentation represents a significant challenge for object-based PCG mapping studies due to the spectral characteristics of these singular structures. Therefore, the assessment of PCG segmentation quality by employing a multiresolution segmentation algorithm (MRS) was addressed in this study. The structure of this work is composed of two differentiated phases. The first phase aimed at testing the performance of eight widely applied supervised segmentation metrics in order to find out which was the best metric for evaluating image segmentation quality over PCG land cover. The second phase focused on examining the effect of several factors (reflectance storage scale, image spatial resolution, shape parameter of MRS, study area, and image acquisition season) and their interactions on PCG segmentation quality through a full factorial analysis of variance (ANOVA) design. The analysis considered two different study areas (Almeria (Spain) and Antalya (Turkey)), seasons (winter and summer), image spatial resolution (high resolution and medium resolution), and reflectance storage scale (Percent and 16Bit formats). Regarding the results of the first phase, the Modified Euclidean Distance 2 (MED2) was found to be the best metric to evaluate PCG segmentation quality. The results coming from the second phase revealed that the most critical factor that affects MRS accuracy was the interaction between reflectance storage scale and shape parameter. Our results suggest that the Percent reflectance storage scale, with digital values ranging from 0 to 100, performed significantly better than the 16Bit reflectance storage scale (0 to 10,000), both in the visual interpretation of PCG segmentation quality and in the quantitative assessment of segmentation accuracy. [ABSTRACT FROM AUTHOR]

Landslide detection is a hot topic in the remote sensing community, particularly with the current rapid growth in volume (and variety) of Earth observation data and the substantial progress of computer vision. Deep learning algorithms, especially fully convolutional networks (FCNs), and variations like the ResU-Net have been used recently as rapid and automatic landslide detection approaches. Although FCNs have shown cutting-edge results in automatic landslide detection, accuracy can be improved by adding prior knowledge through possible frameworks. This study evaluates a rule-based object-based image analysis (OBIA) approach built on probabilities resulting from the ResU-Net model for landslide detection. We train the ResU-Net model using a landslide dataset comprising landslide inventories from various geographic regions, including our study area and test the testing area not used for training. In the OBIA stage, we first calculate land cover and image difference indices for pre-and post-landslide multi-temporal images. Next, we use the generated indices and the resulting ResU-Net probabilities for image segmentation; the extracted landslide object candidates are then optimized using rule-based classification. In the result validation section, the landslide detection of the proposed integration of the ResU-Net with a rule-based classification of OBIA is compared with that of the ResU-Net alone. Our proposed approach improves the mean intersection-over-union of the resulting map from the ResU-Net by more than 22%.

Land use and land cover (LULC) information is a fundamental component of environmental research relating to urban planning, agricultural sustainability, and natural hazards assessment. In particular, remote sensing technology has demonstrated a powerful capacity for LULC modeling with a corresponding increase in sensor number and type. Here, an advanced convolutional neural network (CNN) deep learning model was developed in combination with object-based image analysis (OBIA) to map LULC in Ain Témouchent coastal area, western Algeria, using sentinel-2 and Pléiades imagery data. First, the CNN model was constructed based on convolution, hidden, and max pooling layers. The parameters of CNN architecture were optimized to improve the model for further processing. Then, based on high levels of CNN feature extraction, the OBIA was applied to classify the segmented objects, and detect the LULC features. Furthermore, machine learning methods, including random forest and support vector machines were tested for comparison. The proposed method achieved a high overall accuracy (93.5%) using Pléiades imagery, revealing significant improvements compared to other machine learning techniques. Accordingly, it was concluded that the method proposed here is useful for LULC detection, and can be applied at larger scales in coastal areas. The derived maps can also inform regional and national-level decision making.

The advancement of deep learning (DL) technology and Unmanned Aerial Vehicles (UAV) remote sensing has made it feasible to monitor coastal wetlands efficiently and precisely. However, studies have rarely compared the performance of DL with traditional machine learning (Pixel-Based (PB) and Object-Based Image Analysis (OBIA) methods) in UAV-based coastal wetland monitoring. We constructed a dataset based on RGB-based UAV data and compared the performance of PB, OBIA, and DL methods in the classification of vegetation communities in coastal wetlands. In addition, to our knowledge, the OBIA method was used for the UAV data for the first time in this paper based on Google Earth Engine (GEE), and the ability of GEE to process UAV data was confirmed. The results showed that in comparison with the PB and OBIA methods, the DL method achieved the most promising classification results, which was capable of reflecting the realistic distribution of the vegetation. Furthermore, the paradigm shifts from PB and OBIA to the DL method in terms of feature engineering, training methods, and reference data explained the considerable results achieved by the DL method. The results suggested that a combination of UAV, DL, and cloud computing platforms can facilitate long-term, accurate monitoring of coastal wetland vegetation at the local scale. [ABSTRACT FROM AUTHOR]

Seabed sedimentary bedforms (SSBs) are strong indicators of current flow (direction and velocity) and can be mapped in high resolution using multibeam echosounders. Many approaches have been designed to automate the classification of such SSBs imaged in multibeam echosounder data. However, these classification systems only apply a geomorphological contextualisation to the data without making direct assertions on the velocities of benthic currents that form these SSBs. Here, we apply an object-based image analysis (OBIA) workflow to derive a geomorphological classification of SSBs in the Moira Mounds area of the Belgica Mound Province, NE Atlantic through k-means clustering. Cold-water coral reefs as sessile filter-feeders benefit from strong currents are often found in close association with sediment wave fields. This OBIA provided the framework to derive SSB wavelength and wave height, these SSB attributes were used as predictor variables for a multiple linear regression to estimate current velocities. Results show a bimodal distribution of current flow directions and current speed. Furthermore, a 5 k-means classification of the SSB geomorphology exhibited an imprinting of current flow consistency which altered throughout the study site due to the interaction of regional, local, and micro scale topographic steering forces. This study is proof-of-concept for an assessment tool applied to vulnerable marine ecosystems but has wider applications for applied seabed appraisals and can inform management and monitoring practice across a variety of spatial and temporal scales. Deriving spatial patterns of hydrodynamic processes from widely available multibeam echosounder maps is pertinent to many avenues of research including scour predictions for offshore structures such as wind turbines, sediment transport modelling, benthic fisheries, e.g., scallops, cable route and pipeline risk assessment and habitat mapping. [ABSTRACT FROM AUTHOR]

Abstract Extensive road construction works recently took place in the remote eastern part of the Peruvian Cordillera Blanca, aiming at a better connection of isolated mountain communities with regional administrative centres. Here we document and characterize landslides associated with these road construction efforts in the Río Lucma catchment, Peru. We show that a total area of 321,332 m2 has been affected by landslides along the 47.1 km of roads constructed between 2015 and 2018. While landslides downslope the roads (48.2%) and complex landslides crossing the roads (46.4%) were the most frequent landslide types in relation to the position of the road; slide-type movement (60.7%) prevails over the flow-type movement (39.3%). Timewise, we found that 75.0% of landslides were observed simultaneously with road construction work, while the remaining 25.0% occurred up to seven months after the roads had been constructed. We plotted the lagged occurrence of these subsequent landslides against precipitation data, showing that 85.7% of them were observed during the wet season (November to April). We conclude that the majority of mapped landslides were directly associated with road constructions and that the road constructions also may set preconditions for landslides, which mainly occurred during the subsequent wet season.

The local climate zones (LCZs) system, a standard framework characterizing urban form and environment, effectively promotes urban remote sensing research, especially urban heat island (UHI) research. However, whether mapping with objects is more advantageous than with pixels in LCZ mapping remains uncertain. This study aims to compare object-based and pixel-based LCZ mapping with multi-source data in detail. By comparing the object-based method with the pixel-based method in 50 and 100 m, respectively, we found that the object-based method performed better with overall accuracy (OA) higher at approximately 2% and 5%, respectively. In per-class analysis, the object-based method showed a clear advantage in the land cover types and competitive performance in built types while LCZ2, LCZ5, and LCZ6 performed better with the pixel-based method in 50 m. We further employed correlation-based feature selection (CFS) to evaluate feature importance in the object-based paradigm, finding that building height (BH), sky view factor (SVF), building surface fraction (BSF), permeable surface fraction (PSF), and land use exhibited high selection frequency while image bands were scarcely selected. In summary, we concluded that the object-based method is capable of LCZ mapping and performs better than the pixel-based method under the same training condition unless in under-segmentation cases. [ABSTRACT FROM AUTHOR]

With industrialization and urbanization, the competition among land production, living, and ecological (PLE) spaces has intensified. Particularly in ecological reserves, competition among various types of land use restricts the coordinated development of PLE space. To explore spatial sustainable development, this study starts from a PLE spatial perspective, based on Landsat long time series images. Object-based image analysis (OBIA) and landscape index analysis were selected to monitor the spatial and temporal land use and landscape pattern changes in the Poyang Lake region (PYL region) from 1989 to 2020. The RF-Markov-FLUS coupled model was used to simulate spatial changes in 2030 under four scenarios: production space priority (PSP), living space priority (LSP), ecological space priority (ESP), and an integrated development (ID). Finally, the goal-problem-principle was used to enhance PLE space. The results showed that: (1) production space and ecological spaces decreased in general from 1989 to 2020 by 3% and 7%, respectively; living space increased by 11%. (2) From 1989 to 2020, the overall landscape spread in the Poyang Lake (PYL) area decreased, connectivity decreased, fragmentation increased, landscape heterogeneity increased, and landscape geometry became more irregular. (3) Compared with the other three scenarios, the ID scenario maintained steady production space growth in 2030, the expansion rate of living space slowed, and the area of ecological space decreased the least. (4) Spatial pattern optimization should start with three aspects: the transformation of the agricultural industry, improving the efficiency of urban land use, and establishing communities of "mountains, water, forests, fields, lakes and grasses". The results provide scientific planning and suggestions for the future ecological protection of Poyang Lake area with multiple scenarios and perspectives. [ABSTRACT FROM AUTHOR]

Landslide extraction is one of the most popular topics in remote sensing. Numerous techniques have been proposed to manage the landslide identification problem. However, most aim to extract landslides that have already occurred or delineate the potential landslide manually. It is greatly important to identify and delineate potential landslides automatically, which has not been investigated. In this paper, we propose an automatic identification and delineation method, i.e., object-based image analysis (OBIA) of potential landslides by integrating optical imagery with a deformation map. We applied a deformation map generated by the interferometric synthetic aperture radar (InSAR) technique, rather than the digital elevation model (DEM) for landslide segmentation. Then, we used a classification and regression tree (CART) model with the spectral, spatial, contextual and deformation characteristics for landslide classification. For accuracy assessment, we implemented the evaluation indicators of recall and precision. The proposed method is verified in both specific landslide-prone regions (Jinpingzi and Shuanglongtan landslides) and a large catchment of the Jinsha River, China. By comparing our results with the ones using purely optical imagery, the precision of the Jinpingzi landslide is improved by 14.12%, and the recall and precision of the Shuanglongtan landslide are improved by 3.1% and 3.6%, respectively, and the recall for the large catchment is improved by 9.95%. Our method can improve delineation of potential landslides significantly, which is crucial for landslide early warning and prevention. [ABSTRACT FROM AUTHOR]

Long-term spatial studies are crucial for understanding how the Earth's surface has changed. Before satellite imagery, landscapes were monitored using black and white (B&W) aerial photographs. However, surveys were infrequent and image analysis was a manual process that was both time-consuming and costly. In this study, we created a composite of high spatial resolution (0.5–0.75 m) B&W aerial images from 1939–1944, covering about 91% of Kruger National Park (KNP)'s nearly 2 million ha. We used this to produce the first historical woody cover (tall trees and shrubs) map of KNP, which until now was only partially understood through fragmented descriptions in period literature and small-area case studies. We established a supervised learning workflow using Google Earth Engine (GEE) which included performing an Object-based Image Analysis (OBIA) with a Random Forest classifier. This approach, enhanced by integrating texture, shape, neighboring features, and spectral variables into the training/validation dataset, enabled the identification of woody vegetation from B&W landscape objects. To enhance accuracy, we guided our sampling method using vegetation types with comparable woody cover and species composition. Initially, we tested our method on a smaller set of images (25 km2), and after confirming its effectiveness, we then expanded the approach to cover all available historical aerial imagery. Our results show that in 1939–1944, 26% of KNP was covered in woody vegetation (overall accuracy of 89%, producer's accuracy (non-woody = 88%, woody = 90%), and user's accuracy (non-woody = 90%, woody = 87%)). The importance of geological substrate in driving vegetation pattern is reflected in a higher woody cover percentage on granite (28%) than on basalt (21%) soils, with the lowest woody cover on northern basalts (11%) and the highest on north-central granites (32%). This study highlights the potential of GEE and OBIA for analyzing large-area, high spatial resolution B&W aerial photographs in a systematic and efficient manner and the importance of creating large-scale historical land cover baselines to support environmental planning and landscape management. • Historical aerial images provide valuable insight into long-term ecosystem changes. • First historical woody cover map of Kruger National Park, South Africa (1939–1944). • Object-based image analysis applied to large-area black-and-white aerial images. • Supervised learning workflow using open-source geospatial platform Google Earth Engine. • Applications for large-area land cover assessments and environmental planning. [ABSTRACT FROM AUTHOR]

Recent landslide detection studies have focused on pixel-based deep learning (DL) approaches. In contrast, intuitive annotation of landslides from satellite imagery is based on distinct features rather than individual pixels. This study examines the feasibility of the integration framework of a DL model with rule-based object-based image analysis (OBIA) to detect landslides. First, we designed a ResU-Net model and then trained and tested it in the Sentinel-2 imagery. Then we developed a simple rule-based OBIA with only four rulesets, applying it first to the original image dataset and then to the same dataset plus the resulting ResU-Net heatmap. The value of each pixel in the heatmap refers to the probability that the pixel belongs to either landslide or non-landslide classes. Thus, we evaluate three scenarios: ResU-Net, OBIA, and ResU-Net-OBIA. The landslide detection maps from three different classification scenarios were compared against a manual landslide inventory map using thematic accuracy assessment metrics: precision, recall, and f1-score. Our experiments in the testing area showed that the proposed integration framework yields f1-score values 8 and 22 percentage points higher than those of the ResU-Net and OBIA approaches, respectively. [ABSTRACT FROM AUTHOR]

The availability and usage of optical very high spatial resolution (VHR) satellite images for efficient support of refugee/IDP (internally displaced people) camp planning and humanitarian aid are growing. In this research, an integrated approach was used for dwelling classification from VHR satellite images, which applied the preliminary results of a convolutional neural network (CNN) model as input data for an object-based image analysis (OBIA) knowledge-based semantic classification method. Unlike standard pixel-based classification methods that usually are applied for the CNN model, our integrated approach aggregates CNN results on separately delineated objects as the basic units of a rule-based classification, to include additional prior-knowledge and spatial concepts in the final instance segmentation. An object-based accuracy assessment methodology was used to assess the accuracy of the classified dwelling categories on a single object-level. Our findings reveal accuracies of more than 90% for each applied parameter of precision, recall and F1-score. We conclude that integrating the CNN models with the OBIA capabilities can be considered an efficient approach for dwelling extraction and classification, integrating not only sample derived knowledge but also prior-knowledge about refugee/IDP camp situations, like dwellings size constraints and additional context.

Mangrove forest (MF) extents and distributions are fundamental for conservation and restoration efforts. According to previous studies, both the commercial Gaofen-2 (GF-2) imagery (0.8 m spatial resolution and 4 spectral bands) and freely accessed Sentinel-2 (S2) imagery (10 m spatial resolution and 13 spectral bands) have been successfully used to map MFs. However, the efficiency and accuracy of MF mapping based on these two data is not clear, especially for large-scale applications. To address this issue, first, we developed a robust classification approach by integrating object-based image analysis (OBIA) and random forest (RF) algorithm; and then, applied this approach to GF-2 and S2 images to map the extents of MF along the entire coasts of Guangxi, China, respectively; at last, compared the efficiency and accuracy of GF-2 and S2 imagery in MF mapping. Results showed that: first, based on OBIA and RF integrated classification approach both MF maps derived from GF-2 and S2 obtained high mapping accuracies (the overall accuracy was 96% and 94%, respectively); second, areal extent of MFs in Guangxi extracted from GF-2 and S2 images was 8182 and 8040 ha, respectively; third, GF-2 imagery has extraordinary abilities in detecting fragmented MF patches located along landward and seaward edges; and finally, S2 imagery performed better in detecting seaward submerged MFs and separating MF from terrestrial vegetation. Results and conclusions of this study can provide basic considerations for selecting appropriate data source in MF or wetland vegetation mapping tasks.

The tropical cyclone Idai caused severe floods in Mozambique in March 2019. Sentinel-1 and Sentinel-2 images are processed to monitor the flood disaster in Pungue and Buzi rivers by combining the object-based image analysis approach and the decision tree algorithm. Water is preliminarily extracted from Sentinel-1 image, and shadows of mountain and buildings in the study area are extracted from Sentinel-2 image. Mountain shadow is extracted based on the decision tree classification rules constructed by the digital elevation model and the index model, while building shadow is extracted by constructing the decision tree classification rules using the features of objects. Water extraction results are combined with shadows to eliminate confusing shadows in the preliminary extraction to obtain the accurate flood extent. Sentinel-2 images are used to classify land use types in multiple periods before and after the flood and analyze the disaster by combining with the change information of the water. Land use type changes are analyzed and predicted with the CA-Markov model. The results show that the maximum submerged area was 3.5 times of the normal water area, and that most areas were submerged for more than 10 d. The area between Pungue and Buzi rivers were severely affected, where a large number of crops and villages were submerged. Grassland and cropland were the most seriously submerged. The overall accuracy of extracted water results ranges from 86% to 92%. The results indicated that the combining method can effectively suppress the influence of shadows on water extraction results.

Glacial landforms are a significant element of landscape in many regions of Earth. The increasing availability of high-resolution digital elevation models (DEMs) provides an opportunity to develop automated methods of glacial landscape exploration and classification. In this study, we aimed to: 1) identify glacial landforms based on high-resolution DEM datasets; 2) determine relevant geomorphometric and spectral parameters and object-based features for the mapping of glacial landforms; and 3) develop an accurate workflow for glacial landform classification based on DEM. The developed methodology included the extraction of secondary features from DEM, feature selection with the Boruta algorithm, object-based image analysis, and random forest supervised classification. We applied the workflow for three study sites: one in Svalbard and two in Poland. It allowed the identification of six categories of glacial landforms: till plains, end moraines, hummocky moraines, outwash/glaciolacustrine plains, valleys, and kettle holes. The majority of relevant secondary features represented DEM spectral parameters calculated from 2-D Fourier analysis. The supervised classification models with the highest performance exhibited up to 96% overall accuracy with regard to a groundtruth dataset. This study showed that glacial landforms can be identified using novel image-processing methodology and spectral parameters of high-resolution DEM. The complete classification workflow developed herein provides a solution for the transparent generation of thematic maps of glacial landforms that may be reproducible and transferrable to various glacial regions worldwide. [ABSTRACT FROM AUTHOR]

Turning Earth observation (EO) data consistently and systematically into valuable global information layers is an ongoing challenge for the EO community. Recently, the term ‘big Earth data’ emerged to describe massive EO datasets that confronts analysts and their traditional workflows with a range of challenges. We argue that the altered circumstances must be actively intercepted by an evolution of EO to revolutionise their application in various domains. The disruptive element is that analysts and end-users increasingly rely on Web-based workflows. In this contribution we study selected systems and portals, put them in the context of challenges and opportunities and highlight selected shortcomings and possible future developments that we consider relevant for the imminent uptake of big Earth data.

Accurate mapping of crop distribution on Earth's surface aids in predicting grain production. Pattern classification along with remote sensing imagery can facilitate traditional manual field measurement techniques using machine learning. With the rapid increase in satellite sensor resolution, the object-based classification paradigm has increasingly been applied. However, scale parameter selection is always a difficult part of the object-based classification. Based on ensemble learning, this study proposes a classification method using the multiscale object-based weighted method which includes manual digitizing of crop distribution in the southern region of Jishan County, Shanxi Province, China, applying Gaofen-2 (GF-2) images. This method initially uses estimations of the scale parameter (ESP) tool to select “good” scales, defined here as “preferred” scales, after which feature subsets are screened by each preferred scale as the input of multiple classifiers and classifies. Finally, all classification results are then fused. Our research results indicate that: 1) Feature importance values are sorted differently at different preferred scales; 2) accuracy differences become clear when different preferred scales are combined with different classifiers, and determining the “best” single appropriate scale is generally difficult; 3) accuracy of the multiscale weighted classification method is higher compared to the single preferred scale approach. Furthermore, ensemble learning can be achieved using this method on multiple scales and on multiple classifiers. With this method, procedures that necessitate the selection of segmentation scales and the selection and optimization of classifiers can be skipped altogether.

Accurate and reliable greenhouse mapping using remotely sensed data and image classification methods has a significant role since it can comprehensively improve the urban and rural planning, and sustainable natural resource and agricultural management. This research is mainly focused on the determination of greenhouses from SPOT-7 and Sentinel-2 MultiSpectral Instrument (MSI) images by using an object-based image classification method with three different classifiers which are k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) in the selected test region. First, the image acquired by using multi-resolution segmentation. Second, spectral features, textural features, and remote sensing indices were obtained for each image object. Third, different classifiers were employed to classify greenhouses. Then, classification accuracy assessment analysis was conducted to test the agreement between the classified data and field collected data using the confusion matrix. The results highlighted that the KNN and RF classifier have a slightly higher overall accuracy (OA) and Kappa statistics for SPOT-7 image with the 91.43% and 0.88. Furthermore, the KNN classifier for Sentinel-2 MSI image has the highest OA and Kappa statistics of 88.38% and 0.83. The achieved results underlined the potential of Sentinel-2 MSI and SPOT-7 data for object-based greenhouse mapping using different machine learning classifiers in the Mediterranean Region.

The timely detection and mapping of surface water bodies from Polarimetric Synthetic Aperture Radar (PolSAR) images are of great significance for emergency management and post-disaster restoration tasks. Though various methods have been proposed in previous years, there are still some inherent flaws. Thus, this paper proposes a new surface water extraction method based on superpixels and Graph Convolutional Networks (GCN). First, the PolSAR images are segmented to generate superpixels as the basic unit of classification, and the graph structure data are established according to their connection to superpixels. Then, the features of each superpixel are extracted. Finally, a GCN is used to classify each superpixel unit using node features and their relationships. This study conducted experiments on a sudden flooding event due to heavy rain and a lake in the city. Detailed verification was carried out. Compared to traditional methods, the recall was improved by 3% while maintaining almost 100% accuracy in complex flood areas. The results show that the proposed method of surface water extraction from PolSAR images has great advantages, acquiring higher accuracy and better boundary adherence in cases of fewer samples. This paper also illustrates the advantage of using GCN to mine the contextual information of classification objects.

Plastic-covered greenhouse (PCG) segmentation represents a significant challenge for object-based PCG mapping studies due to the spectral characteristics of these singular structures. Therefore, the assessment of PCG segmentation quality by employing a multiresolution segmentation algorithm (MRS) was addressed in this study. The structure of this work is composed of two differentiated phases. The first phase aimed at testing the performance of eight widely applied supervised segmentation metrics in order to find out which was the best metric for evaluating image segmentation quality over PCG land cover. The second phase focused on examining the effect of several factors (reflectance storage scale, image spatial resolution, shape parameter of MRS, study area, and image acquisition season) and their interactions on PCG segmentation quality through a full factorial analysis of variance (ANOVA) design. The analysis considered two different study areas (Almeria (Spain) and Antalya (Turkey)), seasons (winter and summer), image spatial resolution (high resolution and medium resolution), and reflectance storage scale (Percent and 16Bit formats). Regarding the results of the first phase, the Modified Euclidean Distance 2 (MED2) was found to be the best metric to evaluate PCG segmentation quality. The results coming from the second phase revealed that the most critical factor that affects MRS accuracy was the interaction between reflectance storage scale and shape parameter. Our results suggest that the Percent reflectance storage scale, with digital values ranging from 0 to 100, performed significantly better than the 16Bit reflectance storage scale (0 to 10,000), both in the visual interpretation of PCG segmentation quality and in the quantitative assessment of segmentation accuracy.

Abstract Background Almond is an emerging crop due to the health benefits of almond consumption including nutritional, anti-inflammatory, and hypocholesterolaemia properties. Traditional almond producers were concentrated in California, Australia, and Mediterranean countries. However, almond is currently present in more than 50 countries due to breeding programs have modernized almond orchards by developing new varieties with improved traits related to late flowering (to reduce the risk of damage caused by late frosts) and tree architecture. Almond tree architecture and flowering are acquired and evaluated through intensive field labour for breeders. Flowering detection has traditionally been a very challenging objective. To our knowledge, there is no published information about monitoring of the tree flowering dynamics of a crop at the field scale by using color information from photogrammetric 3D point clouds and OBIA. As an alternative, a procedure based on the generation of colored photogrammetric point clouds using a low cost (RGB) camera on-board an unmanned aerial vehicle (UAV), and an semi-automatic object based image analysis (OBIA) algorithm was created for monitoring the flower density and flowering period of every almond tree in the framework of two almond phenotypic trials with different planting dates. Results Our method was useful for detecting the phenotypic variability of every almond variety by mapping and quantifying every tree height and volume as well as the flowering dynamics and flower density. There was a high level of agreement among the tree height, flower density, and blooming calendar derived from our procedure on both fields with the ones created from on-ground measured data. Some of the almond varieties showed a significant linear fit between its crown volume and their yield. Conclusions Our findings could help breeders and researchers to reduce the gap between phenomics and genomics by generating accurate almond tree information in an efficient, non-destructive, and inexpensive way. The method described is also useful for data mining to select the most promising accessions, making it possible to assess specific multi-criteria ranking varieties, which are one of the main tools for breeders.

The agricultural landscape can be interpreted at different semantic levels, such as fine low-level crop (LLC) classes (e.g., Wheat, Almond, and Alfalfa) and broad high-level crop (HLC) classes (e.g., Winter crops, Tree crops, and Forage). The LLC and HLC are hierarchically correlated with each other, but such intrinsically hierarchical relationships have been overlooked in previous crop classification studies in remote sensing. In this research, a novel Iterative Deep Learning (IDL) framework was proposed for the classification of complex agricultural landscapes using remotely sensed imagery. The IDL adopts an object-based convolutional neural network (OCNN) as the basic classifier for both the LLC and HLC classifications, which has the advantage of maintaining precise crop parcel boundaries. In IDL, the HLC classification implemented by the OCNN is conditional upon the LLC classification probabilities, whereas the HLC probabilities combined with the original imagery are, in turn, re-used as inputs to the OCNN to enhance the LLC classification. Such an iterative updating procedure forms a Markov process, where both the LLC and HLC classifications are refined and evolve collaboratively. The effectiveness of the IDL was tested on two heterogeneous agricultural fields using fine spatial resolution (FSR) SAR and optical imagery. The experimental results demonstrate that the iterative process of IDL helps to resolve contradictions within the class hierarchies. The new proposed IDL consistently increased the accuracies of both the LLC and HLC classifications with iteration, and achieved the highest accuracies for each at four iterations. The average overall accuracies were 88.4% for LLC and 91.2% for HLC, for both study sites, far greater than the accuracies of the state-of-the-art benchmarks, including the pixel-wise CNN (81.7% and 85.9%), object-based image analysis (OBIA) (84.0% and 85.8%), and OCNN (84.0% and 88.4%). To the best of our knowledge, the proposed model is the first to identify and use the relationship between the class levels in an ontological hierarchy in a remote sensing classification process. It is applied here to increase progressively the accuracy of classification at two levels for a complex agricultural landscape. As such IDL represents an entirely new paradigm for remote sensing image classification. Moreover, the promising results demonstrate the great potential of the proposed IDL with wide application prospect.

Spartina alterniflora (S. alterniflora), a prevailing invasive species in the coastal zones, has resulted in significant ecosystem degradation and economic losses since its introduction to China in 1979. Among the existing studies that incorporate remote sensing to map S. alterniflora, the pixel-based phenological feature composite method (Ppf-CM) has proved to be successful due to its merits to overcome cloud contamination while exaggerating the spectral separability between S. alterniflora and its co-dominant native species. However, one major limitation of the Ppf-CM method is that it extracts phenological features from a single-pixel without accounting for its surrounding geospatial information that proved essential for more accurate mapping. In this study, we aim to ameliorate this problem by incorporating geometric, texture, and contextual information. To this end, we developed a new object-based phenological feature composite method (OPpf-CM). Specifically, we first generated a composite image by stacking two images that were respectively acquired during the distinctive phenological periods of S. alterniflora. Then we derived spectrally homogenous objects on the composite image through an unsupervised multiscale segmentation method. Various features derived from objects served as the input of support vector machine (SVM) classifier to produce a S. alterniflora map. To evaluate the performance of OPpf-CM, we carried out a comparison of classification performance between our developed OPpf-CM method and the previously developed Ppf-CM one (Tian et al., 2020) with the aid of visual interpretation and accuracy statistics (i.e. confusion matrix). The results showed that OPpf-CM achieved a higher overall accuracy (98%) than Ppf-CM (96.67%) when validated with the ground reference data that was visually interpreted by the high spatial resolution imagery and field survey. Meanwhile, the identification of fragmented S. alterniflora patches along with mixed-cover areas can be significantly improved with the OPpf-CM method. We envision that the developed object-based spectral-phenological feature has the potential to be applied to mapping a wide spectrum of coastal vegetations.

Seabed sedimentary bedforms (SSBs) are strong indicators of current flow (direction and velocity) and can be mapped in high resolution using multibeam echosounders. Many approaches have been designed to automate the classification of such SSBs imaged in multibeam echosounder data. However, these classification systems only apply a geomorphological contextualisation to the data without making direct assertions on the velocities of benthic currents that form these SSBs. Here, we apply an object-based image analysis (OBIA) workflow to derive a geomorphological classification of SSBs in the Moira Mounds area of the Belgica Mound Province, NE Atlantic through k-means clustering. Cold-water coral reefs as sessile filter-feeders benefit from strong currents are often found in close association with sediment wave fields. This OBIA provided the framework to derive SSB wavelength and wave height, these SSB attributes were used as predictor variables for a multiple linear regression to estimate current velocities. Results show a bimodal distribution of current flow directions and current speed. Furthermore, a 5 k-means classification of the SSB geomorphology exhibited an imprinting of current flow consistency which altered throughout the study site due to the interaction of regional, local, and micro scale topographic steering forces. This study is proof-of-concept for an assessment tool applied to vulnerable marine ecosystems but has wider applications for applied seabed appraisals and can inform management and monitoring practice across a variety of spatial and temporal scales. Deriving spatial patterns of hydrodynamic processes from widely available multibeam echosounder maps is pertinent to many avenues of research including scour predictions for offshore structures such as wind turbines, sediment transport modelling, benthic fisheries, e.g., scallops, cable route and pipeline risk assessment and habitat mapping.

Image segmentation has been an important procedure in object-based image analysis (OBIA), which takes image object as a processing unit. The spatial scale in image segmentation has great importance in OBIA. Due to the high heterogeneity and large dynamic range of polarimetric synthetic aperture radar (PolSAR) images, it is often difficult to choose optimal spatial scales. This letter proposes a polarimetric semivariogram-based spatial scale selection method for PolSAR image segmentation. The optimal spatial bandwidth parameter in the mean-shift algorithm is pre-estimated based on the combined polarimetric and statistical analysis of PolSAR images. By implementing a quantitative evaluation of segmentation result, the effectiveness of the proposed method in optimal spatial bandwidth selection for PolSAR image segmentation is verified. Experiments on both the EMISAR and UAVSAR L-band PolSAR data sets testify the validity of the proposed adaptive optimal bandwidth selection strategy for PolSAR images. [ABSTRACT FROM AUTHOR]

Mapping informal settlements is crucial for resource and utility management and planning. In 2003, the UN-Habitat developed a process for mapping and monitoring urban inequality to support reporting against the sustainable development goals (SDGs). Informal settlement indicators are used as a framework to carry out image analysis, and include vegetation extent, lacunarity of housing structures / vacant land, road segment type and materials, texture measures of built-up areas, roofing extent of built-up areas and dwelling size. Object-based image analysis (OBIA) methods are recommended to identify informal settlements. This paper documents the application of OBIA to map informal settlements, drawing on the ontology of Kohli et al. (2012) and the indicators of Owen and Wong (2013) for a Middle Eastern city. Three informal settlements with different land use histories were selected to represent old and new informal settlements in the city of Jeddah, Saudi Arabia. Vegetation extent was the most successful indicator detected, with 100% producer accuracy and over 84% user accuracy, followed by the road network, with 84% producer and user accuracies in older informal settlements and 73% producer accuracy and 96% user accuracy across all case studies. Lacunarity of housing structures / vacant land was detected well in informal settlements. The texture measure indicator was detected using $\hbox{GLC}\hbox{M}_{{\rm Ent}}\lpar R\rpar $ with low producer accuracy across all case studies. The roofing extent of the built-up area is detected with better producer and user accuracies than texture measures. The dwellings size indicator generally failed to distinguish formal from informal settlements. Informal and formal were distinguished with an overall accuracy of 83%. This research concludes that OBIA is a useful method to map informal settlement indicators in Middle Eastern cities. However, a generic ruleset for mapping informal settlements remains elusive, and each indicator requires significant localised ‘tuning’.

The local climate zones (LCZs) system, a standard framework characterizing urban form and environment, effectively promotes urban remote sensing research, especially urban heat island (UHI) research. However, whether mapping with objects is more advantageous than with pixels in LCZ mapping remains uncertain. This study aims to compare object-based and pixel-based LCZ mapping with multi-source data in detail. By comparing the object-based method with the pixel-based method in 50 and 100 m, respectively, we found that the object-based method performed better with overall accuracy (OA) higher at approximately 2% and 5%, respectively. In per-class analysis, the object-based method showed a clear advantage in the land cover types and competitive performance in built types while LCZ2, LCZ5, and LCZ6 performed better with the pixel-based method in 50 m. We further employed correlation-based feature selection (CFS) to evaluate feature importance in the object-based paradigm, finding that building height (BH), sky view factor (SVF), building surface fraction (BSF), permeable surface fraction (PSF), and land use exhibited high selection frequency while image bands were scarcely selected. In summary, we concluded that the object-based method is capable of LCZ mapping and performs better than the pixel-based method under the same training condition unless in under-segmentation cases.

With industrialization and urbanization, the competition among land production, living, and ecological (PLE) spaces has intensified. Particularly in ecological reserves, competition among various types of land use restricts the coordinated development of PLE space. To explore spatial sustainable development, this study starts from a PLE spatial perspective, based on Landsat long time series images. Object-based image analysis (OBIA) and landscape index analysis were selected to monitor the spatial and temporal land use and landscape pattern changes in the Poyang Lake region (PYL region) from 1989 to 2020. The RF-Markov-FLUS coupled model was used to simulate spatial changes in 2030 under four scenarios: production space priority (PSP), living space priority (LSP), ecological space priority (ESP), and an integrated development (ID). Finally, the goal-problem-principle was used to enhance PLE space. The results showed that: (1) production space and ecological spaces decreased in general from 1989 to 2020 by 3% and 7%, respectively; living space increased by 11%. (2) From 1989 to 2020, the overall landscape spread in the Poyang Lake (PYL) area decreased, connectivity decreased, fragmentation increased, landscape heterogeneity increased, and landscape geometry became more irregular. (3) Compared with the other three scenarios, the ID scenario maintained steady production space growth in 2030, the expansion rate of living space slowed, and the area of ecological space decreased the least. (4) Spatial pattern optimization should start with three aspects: the transformation of the agricultural industry, improving the efficiency of urban land use, and establishing communities of “mountains, water, forests, fields, lakes and grasses”. The results provide scientific planning and suggestions for the future ecological protection of Poyang Lake area with multiple scenarios and perspectives.

Landslide extraction is one of the most popular topics in remote sensing. Numerous techniques have been proposed to manage the landslide identification problem. However, most aim to extract landslides that have already occurred or delineate the potential landslide manually. It is greatly important to identify and delineate potential landslides automatically, which has not been investigated. In this paper, we propose an automatic identification and delineation method, i.e., object-based image analysis (OBIA) of potential landslides by integrating optical imagery with a deformation map. We applied a deformation map generated by the interferometric synthetic aperture radar (InSAR) technique, rather than the digital elevation model (DEM) for landslide segmentation. Then, we used a classification and regression tree (CART) model with the spectral, spatial, contextual and deformation characteristics for landslide classification. For accuracy assessment, we implemented the evaluation indicators of recall and precision. The proposed method is verified in both specific landslide-prone regions (Jinpingzi and Shuanglongtan landslides) and a large catchment of the Jinsha River, China. By comparing our results with the ones using purely optical imagery, the precision of the Jinpingzi landslide is improved by 14.12%, and the recall and precision of the Shuanglongtan landslide are improved by 3.1% and 3.6%, respectively, and the recall for the large catchment is improved by 9.95%. Our method can improve delineation of potential landslides significantly, which is crucial for landslide early warning and prevention.