Object-oriented Classification Research Articles

Improved random forest classification model combined with C5.0 algorithm for vegetation feature analysis in non-agricultural environments

In response to the challenges posed by the high computational complexity and suboptimal classification performance of traditional random forest algorithms when dealing with high-dimensional and noisy non-agricultural vegetation satellite data, this paper proposes an enhanced random forest algorithm based on the C5.0 algorithm. The paper focuses on the Liaohe Plain, selecting two distinct non-agricultural landscape patterns in Shenbei New District and Changtu County as research objects. High-resolution satellite data from GF-2 serves as the experimental dataset. This paper introduces an ensemble feature method based on the bagging concept to improve the original random forest classification model. This method enhances the likelihood of selecting features beneficial to classifying positive class samples, avoiding excessive removal of useful features from negative samples. This approach ensures feature importance and model diversity. The C5.0 algorithm is then employed for feature selection, and the enhanced vegetation index (EVI) is utilized for vegetation coverage estimation. Results indicate that employing a multi-scale parameter selection tool, combined with limited field-measured data, facilitates the identification and classification of plant species in forest landscapes. The C5.0 algorithm effectively selects classification features, minimizing information redundancy. The established object-oriented random forest classification model achieves an impressive accuracy of 94.02% on the aerial imagery for forest classification dataset, with EVI-based vegetation coverage estimation demonstrating high accuracy. In experiments on the same test set, the proposed algorithm attains an average accuracy of 90.20%, outperforming common model algorithms such as bidirectional encoder representation from transformer, FastText, and convolutional neural network, which achieve average accuracies ranging from 84.41 to 88.33% in identifying non-agricultural artificial habitat vegetation features. The proposed algorithm exhibits a competitive edge compared to other algorithms. These research findings contribute scientific evidence for protecting agricultural ecosystems and restoring agricultural ecosystem biodiversity.

Aboveground Biomass Inversion Based on Object-Oriented Classification and Pearson–mRMR–Machine Learning Model

Cities play a crucial role in the carbon cycle. Measuring urban aboveground biomass (AGB) is essential for evaluating carbon sequestration. Satellite remote sensing enables large-scale AGB inversion. However, the apparent differences between forest and grassland biomass pose a significant challenge to the accurate estimation of urban AGB using satellite-based data. To address this limitation, this study proposed a novel AGB estimation method using the eastern part of the Zhahe mining area in Huaibei City as the study area, which integrates land cover classification, feature selection, and machine learning modelling to generate high quality biomass maps of different vegetation types in an urban area with complex feature distribution. Utilizing the GEE platform and Sentinel-2 image, we developed an object-oriented machine learning classification algorithm, combining SNIC and GLCM to extract vegetation information. Optimal feature variables for forest and crop-grass AGB inversion were selected using the Pearson–mRMR algorithm. Finally, we constructed nine machine learning models for AGB inversion and selected the model with the highest accuracy to generate the AGB map of the study area. The results of the study are as follows: (1) Compared with the pixel-based classification method, the object-oriented classification method can extract the boundaries of different vegetation types more accurately. (2) Forest AGB is strongly correlated with vegetation indices and physiological parameters, while agri-grass AGB is primarily associated with vegetation indices and vegetation physiological parameters. (3) For forest AGB modelling, the RF-R model outperforms other machine learning models with an R2 of 0.77. For agri-grass AGB modelling, the XGBoost-R model is more accurate, with an R2 of 0.86. (4) The mean forest AGB in the study area was 4.60 kg/m2, while the mean agri-grass AGB was 0.71 kg/m2. High AGB values were predominantly observed in forested areas, which were mainly distributed along roads, waterways, and mountain ranges. Overall, this study contributes to a better understanding of the health of local urban ecosystems and provides valuable insights for ecosystem protection and the sustainable use of natural resources.

Combinations of Feature Selection and Machine Learning Models for Object-Oriented “Staple-Crop-Shifting” Monitoring Based on Gaofen-6 Imagery

This paper combines feature selection with machine learning algorithms to achieve object-oriented classification of crops in Gaofen-6 remote sensing images. The study provides technical support and methodological references for research on regional monitoring of food crops and precision agriculture management. “Staple-food-shifting” refers to the planting of other cash crops on cultivated land that should have been planted with staple crops such as wheat, rice, and maize, resulting in a change in the type of arable land cultivated. An accurate grasp of the spatial and temporal patterns of “staple-food-shifting” on arable land is an important basis for rationalizing land use and protecting food security. In this study, the Shihezi Reclamation Area in Xinjiang is selected as the study area, and Gaofen-6 satellite images are used to study the changes in the cultivated area of staple food crops and their regional distribution. Firstly, the images are segmented at multiple scales and four types of features are extracted, totaling sixty-five feature variables. Secondly, six feature selection algorithms are used to optimize the feature variables, and a total of nine feature combinations are designed. Finally, k-Nearest Neighbor (KNN), Random Forest (RF), and Decision Tree (DT) are used as the basic models of image classification to explore the best combination of feature selection method and machine learning model suitable for wheat, maize, and cotton classification. The results show that our proposed optimal feature selection method (OFSM) can significantly improve the classification accuracy by up to 15.02% compared to the Random Forest Feature Importance Selection (RF-FI), Random Forest Recursive Feature Elimination (RF-RFE), and XGBoost Feature Importance Selection (XGBoost-FI) methods. Among them, the OF-RF-RFE model constructed based on KNN performs the best, with the overall accuracy, average user accuracy, average producer accuracy, and kappa coefficient reaching 90.68%, 87.86%, 86.68%, and 0.84, respectively.

Object-Oriented Convolutional Neural Network for Forest Stand Classification Based on Multi-Source Data Collaboration

Accurate classification of forest stand is crucial for protection and management needs. However, forest stand classification remains a great challenge because of the high spectral and textural similarity of different tree species. Although existing studies have used multiple remote sensing data for forest identification, the effects of different spatial resolutions and combining multi-source remote sensing data for automatic complex forest stand identification using deep learning methods still require further exploration. Therefore, this study proposed an object-oriented convolutional neural network (OCNN) classification method, leveraging data from Sentinel-2, RapidEye, and LiDAR to explore classification accuracy of using OCNN to identify complex forest stands. The two red edge bands of Sentinel-2 were fused with RapidEye, and canopy height information provided by LiDAR point cloud was added. The results showed that increasing the red edge bands and canopy height information were effective in improving forest stand classification accuracy, and OCNN performed better in feature extraction than traditional object-oriented classification methods, including SVM, DTC, MLC, and KNN. The evaluation indicators show that ResNet_18 convolutional neural network model in the OCNN performed the best, with a forest stand classification accuracy of up to 85.68%.

Assessing the Efficacy of Pixel-Level Fusion Techniques for Ultra-High-Resolution Imagery: A Case Study of BJ-3A.

Beijing Satellite 3 is a high-performance optical remote sensing satellite with a spatial resolution of 0.3-0.5 m. It can provide timely and independent ultra-high-resolution spatial big data and comprehensive spatial information application services. At present, there is no relevant research on the fusion method of BJ-3A satellite images. In many applications, high-resolution panchromatic images alone are insufficient. Therefore, it is necessary to fuse them with multispectral images that contain spectral color information. Currently, there is a lack of research on the fusion method of BJ-3A satellite images. This article explores six traditional pixel-level fusion methods (HPF, HCS, wavelet, modified-IHS, PC, and Brovey) for fusing the panchromatic image and multispectral image of the BJ-3A satellite. The fusion results were analyzed qualitatively from two aspects: spatial detail enhancement capability and spectral fidelity. Five indicators, namely mean, standard deviation, entropy, correlation coefficient, and average gradient, were used for quantitative analysis. Finally, the fusion results were comprehensively evaluated from three aspects: spectral curves of ground objects, absolute error figure, and object-oriented classification effects. The findings of the research suggest that the fusion method known as HPF is the optimum and appropriate technique for fusing panchromatic and multispectral images obtained from BJ-3A. These results can be utilized as a guide for the implementation of BJ-3A panchromatic and multispectral data fusion in real-world scenarios.

Dynamics of coastal land-based aquaculture pond in China and Southeast Asia from 1990 to 2020

The extensive expansion of coastal land-based aquaculture ponds (CLAP) has resulted in substantial wetland loss. To effectively monitor the dynamics of CLAP on a large scale, critical spatial information derived from continuous datasets is essential. Here, we generate the inaugural map depicting the changes in aquaculture pond coverage across the coastal regions both of China and Southeast Asia from 1990 to 2020 by utilizing the long time-series Landsat archive with an object-oriented hierarchical classification method. We extracted coastal water bodies using the Otsu algorithm and established a water inundation frequency index to eliminate interference from temporary water facilities. This process allowed us to identify potential distribution areas of aquaculture ponds. To precisely map the spatial distribution of CLAP within these identified areas, we employed an object-oriented K-nearest neighbor approach with spectral, geometric, and water index features as classification features. The cumulative coverage of CLAP in China and Southeast Asia reached 23,121 km2 by 2020, marking a net increase of 12,700 km2 since 1990. Notably, China, Indonesia, and Vietnam emerged as the primary contributors to these changes within our study area. Regions exhibiting dense aquaculture activities are predominantly concentrated in the northern region above 10 degrees latitude and along the eastern coastlines of various countries. This aquaculture pond map reserves fine spatial detail by effectively distinguishing drainage channels, rice seedling fields, and embankments surrounding aquaculture ponds. It serves as a valuable resource for guiding coastal resource management and environmental protection initiatives.

Crop Classification in Mountainous Areas Using Object-Oriented Methods and Multi-Source Data: A Case Study of Xishui County, China

Accurate crop mapping can represent the fundamental data for digital agriculture and ecological security. However, current crop classification methods perform poorly in mountainous areas with small cropland field parcel areas and multiple crops under cultivation. This study proposed a new object-oriented classification method to address this issue, using multi-source data and object features to achieve multi-crop classification in mountainous areas. Firstly, a deep learning method was employed to extract cropland field parcels in mountainous areas. Subsequently, the fusion of multi-source data was carried out based on cropland field parcels, while object features tailored for mountainous crops were designed for crop classification. Comparative analysis indicates that the proposed classification method demonstrates exceptional performance, enabling accurate mapping of various crops in mountainous regions. The F1 score and overall accuracy (OA) of the proposed method are 0.8449 and 0.8502, representing a 10% improvement over the pixel-based random forest classification results. Furthermore, qualitative analysis reveals that the proposed method exhibits higher classification accuracy for smaller plots and more precise delineation of crop boundaries. Finally, meticulous crop mapping of corn, sorghum, rice, and other crops in Xishui County, Guizhou Province, demonstrates the significant potential of the proposed method in crop classification within mountainous scenarios.

Mapping large-scale aquaculture ponds in Jiangsu Province, China: An automatic extraction framework based on Sentinel-1 time-series imagery

Aquaculture holds significant importance in supporting food security, economic development, resource conservation, and ecological balance. However, the rapid expansion of aquaculture ponds has caused many environmental problems. Studies on the trends and spatial distribution of aquaculture ponds in Jiangsu province, China, are limited, and there is a lack of aquaculture datasets with a 10-m resolution. This study aimed to develop a novel assessment framework for mapping aquaculture ponds using the Google Earth Engine (GEE) platform and Sentinel-1 time-series images. We integrated multi-threshold segmentation and object-oriented classification to extract spatial data on aquaculture ponds from 2017 to 2021 in Jiangsu Province. Results showed that (1) local adaptive threshold methods could extract data about water bodies more effectively. Based on the time series of each image element, calculating its water frequency could effectively exclude seasonal water. (2) This method could effectively map aquaculture ponds in Jiangsu Province. The overall identification accuracy was higher than 93%, and the Kappa coefficient was higher than 0.87. These results are in accordance with those in the statistical yearbook. (3) The total aquaculture pond area was largest in 2017 (3404.00 km2) and smallest in 2021 (2939.51 km2). The aquaculture pond area in Jiangsu Province showed a slight downward trend over the five-year period. Aquaculture ponds were mainly distributed in central and southern Jiangsu and the coastal areas, with the highest density at the junction of Yangzhou, Taizhou, and Yancheng. (4) From 2017 to 2021, Aquaculture ponds spanning 104.65 km2 (accounting for 55.28% of the total reduced area) were transformed into wetlands. In the coastal zone. Our results substantiate that aquaculture pond removal can accelerate wetland restoration. This study maximised the identification of aquaculture ponds as independent targets. Taken together, these results can provide a reference for aquaculture green development and tail water management in Jiangsu Province.

Evaluating decadal space-temporal mangrove dynamics using geographic object-based image analysis (GEOBIA) on the Doce River delta-ES, southeastern Brazilian coast

Mangroves are ecosystems present in a large part of the Brazilian coastal zone that are home to a wide diversity of organisms, providing direct and indirect resources, as well as nursery and foraging habitats. Using images in 5-year intervals (2010, 2015, and 2020), the present study carried out a decadal mapping of the remaining mangroves of the Doce River delta along the tidal flats of the Mariricu River, in the coastal region of the city of São Mateus-ES. In this context, object-oriented classification methodology (GEOBIA) was used, which allowed the generation of high-resolution data. This methodology achieved excellent results, as evidenced by the global accuracy numbers and Kappa index, which gave an average of 96.78% and 93.5% respectively; and by low values of disagreement, with an average of 3.22%. The change detection analysis showed alterations in the landscape over time, with 9% of the mangrove areas becoming extinct, 12% of the areas expanding, and 79% of the areas remaining preserved. Therefore, our mapping data are consistent with the data published by the State Institute for the Environment and Water Resources of the State of Espírito Santo (IEMA), as well as with scientific works that recorded areas of reduction and expansion for mangroves, but mostly with large preserved areas. With that, our results demonstrate the highly effective application of geotechnologies for coastal environmental analyses with low cost and high speed.

Susceptibility Mapping of Unhealthy Trees in Jiuzhaigou Valley Biosphere Reserve

Jiuzhaigou Valley is recognized as both a world natural heritage site and a biosphere reserve. Conducting research on vegetation health within its scope can provide a demonstration role for sustainable development research. In this study, we proposed a technology integration approach that combined remote sensing intelligent identification and quantitative retrieval, and achieved vegetation health monitoring and susceptibility mapping of unhealthy trees. Leveraging WorldView-2 high-resolution satellite images, unhealthy trees were elaborately identified through the object-oriented classification method employing spectral and texture features, with F1 Score exceeding 75%. By applying fuzzy operations on indices related to leaf pigment and canopy architecture, we ultimately generated susceptibility maps of unhealthy trees on Sentinel-2 satellite images, with Area Under the Curve (AUC) exceeding 0.85. Our findings underscore that the vegetation health in Jiuzhaigou Valley is predominantly influenced by human activities and geological hazards. The forests of Jiuzhaigou Valley exhibit a certain degree of resilience to geological disasters, while human activities have been continuously exerting adverse effects on forest health in recent years, necessitating heightened attention. The methodology proposed in this study for mapping unhealthy trees susceptibility presents a cost-effective solution that can be readily applied for vegetation health monitoring and early warning in analogous biosphere reserves.

Mapping 30-m cotton areas based on an automatic sample selection and machine learning method using Landsat and MODIS images

ABSTRACT Cotton is one of the most significant cash crops in the world, and it is also the main source of natural fiber for textiles. It is crucial for cotton management to identify the spatiotemporal distribution of cotton planting areas timely and accurately on a fine scale. However, previous research studies have predominantly concentrated on specific years using remote sensing data. Challenges still exist in the extraction of cotton areas for long time series with high accuracy. To address this issue, a novel cotton sample selection method was proposed and the machine learning method is employed to effectively identify the long time series cotton planting areas at a 30-m resolution scale. Bortala and Shuanghe in Xinjiang, China, were selected as the study cases to demonstrate the approach. Specifically, the cropland in this study was extracted by using an object-oriented classification method with Landsat images and the results were optimized as the vectorized boundary of croplands. Then, the cotton samples were selected using the Normalized Difference Vegetation Index (NDVI) series of Moderate Resolution Imaging Spectroradiometer (MODIS) based on its phenological characteristics. Next, cotton was identified based on the croplands from 2000 to 2020 by using the machine learning model. Finally, the performance was evaluated, and the spatiotemporal distribution characteristics of cotton planting areas were analyzed. The results showed that the proposed approach can achieve high accuracy at a fine spatial resolution. The performance evaluation indicated the applicability and suitability of the method, there is a good correlation between the extracted cotton areas and statistical data, and the cotton area of the study area showed an increasing trend. The cotton spatial distribution pattern developed from dispersion to agglomeration. The proposed approach and the derived 30-m cotton maps can provide a scientific reference for the optimization of agricultural management.

Cost–Benefit Evaluation of Walnut and Jujube Orchards under Fruit Tree–Crop Intercropping Conditions in Southern Xinjiang

Fruit planting plays an essential role in achieving zero hunger, ensuring food security, and increasing the income of local people. As one of China’s principal fruit-planting areas, southern Xinjiang possesses more than 80% of the total fruit-planting areas of Xinjiang. However, the spatial distribution, extent, and types of fruit trees remain unknown, generating uncertainty in calculating the economic benefits of orchards in this area. In this paper, we used walnut and jujube orchards under fruit tree–crop intercropping conditions in the Hotan Oasis in southern Xinjiang as the research object. Walnut and jujube orchards were precisely characterized using object-oriented and decision tree classification methods. Then, the economic benefits for farmers were estimated based on field surveys and statistical data. From 2003 to 2020, the area of jujube orchards rapidly increased from 1.91 × 103 ha to 33.59 × 103 ha, while that of walnut orchards steadily increased from 18.05 × 103 ha to 40.24 × 103 ha. The expansion areas of walnut orchards were mainly transformed from other orchards in the oasis, while the expansion areas of jujube orchards mainly originated from newly cultivated land in the desert. The increases in areas and yields largely offset the increase in planting costs and the decrease in purchase prices, resulting in an increasing trend in the total net income of the orchards. From 2003 to 2020, the total net income of walnut orchards increased by 68.96%, and the total net income of jujube orchards significantly increased by 23.37 times. However, the output/input ratios of walnut orchards under intercropping conditions were approximately two times higher than those of jujube orchards under monocropping conditions. The increase in investment slightly offset the decreases in yields and purchase prices, resulting in increases of 5.24% and 18.64% in the output/input ratios of walnuts and jujubes, respectively, in orchards exhibiting standardized cultivation. In the future, it is necessary to significantly expand the area of orchards involving standardized cultivation and improve the yield and quality of fruits, thereby increasing the yields and income levels of local farmers.

Remote sensing methods for striped marine oil spill detection in narrow ship channels

Maritime transport is the backbone of international trade and the global economy. With the increasing frequency of maritime transport, oil spills are on the rise and so is the risk of oil spills in shipping lanes. Therefore, timely oil spill monitoring at the ship channel is of far-reaching significance for marine disaster prevention and control. This study selects oil spill in the ship channel of the northern Yellow Sea as an example and proposes an object-oriented fuzzy logic classification method combining selected multi-feature parameters based on Sentinel-2 data. Firstly, sensitive bands for oil spills are selected to perform multi-scale segmentation of the oil spill object. Then, 30 samples of oil spill objects were uniformly selected in the oil spill area and the average fuzzy membership values were calculated using 11 membership functions by combining the preferred spectral, geometric, texture, and custom features. Finally, five fuzzy logic operators are used to achieve the final classification, while the oil spill misclassification information is processed and compared with the pixel-based SVM and RF algorithms for accuracy. The experimental results show that the oil spill detection based on the “AND” operator is the best compared to other fuzzy operators, with an overall accuracy of 85.19% and a KAPPA coefficient of 0.753. Relative to the pixel-based Support Vector Machine (SVM) and Random Forest (RF) algorithms, the overall accuracy was improved by 15.66% and 11.25%, respectively, and the KAPPA coefficients were improved by 0.072 and 0.161, respectively. The method is feasible for oil spill detection at ship channels and provides technical support for future marine oil spill detection work.

Automatic urban feature extraction using rule-based object-oriented classification: a case study of parts of Pune city, Maharashtra, India

Automatic urban feature extraction using rule-based object-oriented classification: a case study of parts of Pune city, Maharashtra, India

Mangrove forest mapping from object-oriented multi-feature ensemble classification using Sentinel-2 images

Accurate mapping of mangrove forests is crucial for understanding their ecosystem function and developing effective management policies. However, the absence of an operational multi-feature fusion approach and an ensemble classification system restricts the achievement of this goal. This study aims to develop an object-oriented multi-feature ensemble classification scheme (OMEC). First, an enhanced mangrove spectral index (EMSI) is established by analyzing the spectral reflectance differences between mangrove forests and other land cover types. Sentinel-2 images are segmented into objects using the multi-resolution segmentation method. Then, spectral, textural, and geometric features are extracted, and these features (including EMSI) are inputted into the nearest neighbor classifier to implement mangrove classification. The experiment was conducted in three typical mangrove areas in China using Sentinle-2 images. The results demonstrate that EMSI exhibits good spectral separability for mangroves and performs well in the ensemble classification scheme. The overall accuracy of mangrove classification exceeds 90%, with a Kappa coefficient greater than 0.88. The object-oriented multi-feature ensemble classification scheme significantly improves accuracy and exhibits excellent performance. The method enhances the accuracy of mangrove classification, enriches the approach to mangrove remote sensing interpretation, and offers data support and scientific references for the restoration, management, and protection of coastal wetlands.

Analysis of Land Use/Cover Changes and Driving Forces in a Typical Subtropical Region of South Africa

Land use/cover change (LULCC) is an integral part of global environmental change and is influenced by both natural and socioeconomic factors. This study aims to comprehensively analyze land use and land cover (LULC) in Kwazulu-Natal and Mpumalanga provinces in eastern South Africa from 1995 to 2020 and to identify the driving force behind LULCC. Utilizing Landsat series satellite imagery as a data source and based on the Google Earth Engine (GEE) platform and eCognition software 9.0, two different classification methods, pixel-based classification and object-oriented classification, were adopted to gather LULC data every five years. The spatiotemporal characteristics of the data were then analyzed. Using an optimal parameter-based geodetector (OPGD), this study explored the driving factors of LULCC in this region. The results show the following: (1) Of the two classification methods examined, the object-oriented classification had higher accuracy, with an overall accuracy of 80–90%. The pixel-based classification had lower accuracy, with an overall accuracy of 62.33–72.14%. (2) From 1995 to 2020, the area of farmland in the study area showed a fluctuating increase, while the areas of forest and grassland declined annually. The area of constructed land increased annually, whereas the areas of water and unused land fluctuated over time. (3) Socioeconomic factors generally had greater explanatory power than natural factors, with population growth and economic development being the main drivers of LULCC in the region. This study provides a reliable scientific basis for the formulation of sustainable land resource development strategies in the area, as well as for the management and implementation of urban and rural planning, ecological protection, and environmental governance by relevant departments.

Systematic assessment method for post-earthquake damage of regional buildings using adaptive-network-based fuzzy inference system

Rapid damage assessment of regional buildings is critical in post-earthquake rescue and victim resettlement. In this study, a novel rapid damage assessment method for post-earthquake buildings based on multi-types of damage features was proposed. First, the roof-related damage features are extracted from UAV tilt photography with the method of multiscale segmentation and object-oriented classification. Then, the normalized digital surface model was introduced to determine the height-related damage features. Meanwhile, a lightweight CNN model was employed to realize the preliminary evaluation of building facade conditions. Finally, all obtained damage features were taken as inputs to an adaptive-network-based fuzzy inference system for damage assessment. The proposed method was characterized by the capability to comprehensively cover the damage features of regional buildings involved in the evaluation, and thus be able to obtain more accurate judgments than current methods based on a single feature. At the same time, the effectiveness and robustness of the proposed method were evaluated and demonstrated by the field test on the world's largest earthquake site in Beichuan, China, and the prediction of damage level on the testing set achieved an accuracy of 87.1%.

Object-oriented polarimetric SAR image classification via the combination of a pixel-based classifier and a region growing technique

ABSTRACT Land-cover type interpretation by the use of remote sensing image classification techniques is always a hot topic. In this paper, an object-oriented method is presented for fully polarimetric synthetic aperture radar (SAR) image classification. Differing from most of the traditional object-oriented classification algorithms, the proposed method employs an innovative classification strategy that combines a pixel-based classifier and a region growing technique. Firstly, taking each individual pixel as a seed pixel, the homogeneous areas are extracted by a region growing technique. Then, using the information of the pixel-based classification result, the pixels located in each homogeneous area are all assigned to a certain class. Finally, the majority voting strategy is deployed to determine the final class label of each pixel. The experiments conducted on two fully polarimetric SAR images reveal that the proposed classification scheme can obtain pleasing classification accuracy and can provide the classification maps with more homogeneous regions than pixel-based classification.

Optimized Extraction Method of Fruit Planting Distribution Based on Spectral and Radar Data Fusion of Key Time Phase

With China’s fruit tree industry becoming the largest in the world, accurately understanding the spatial distribution of fruit tree growing areas is crucial for promoting socio-economic development and rural revitalization. Remote sensing offers unprecedented opportunities for fruit tree monitoring. However, previous research has mainly focused on UAV and near-ground remote sensing, with limited accuracy in obtaining fruit tree distribution information through satellite remote sensing. In this study, we utilized the Google Earth Engine (GEE) remote sensing cloud platform and integrated data from Sentinel-1, Sentinel-2, and SRTM sources. We constructed a feature space by extracting original band features, vegetation index features, polarization features, terrain features, and texture features. The sequential forward selection (SFS) algorithm was employed for feature optimization, and a combined machine learning and object-oriented classification model was used to accurately extract fruit tree crop distributions by comparing key temporal phases of fruit trees. The results revealed that the backscatter coefficient features from Sentinel-1 had the highest contribution to the classification, followed by the original band features and vegetation index features from Sentinel-2, while the terrain features had a relatively smaller contribution. The highest classification accuracy for jujube plantation areas was observed in November (99.1% for user accuracy and 96.6% for producer accuracy), whereas the lowest accuracy was found for pear tree plantation areas in the same month (93.4% for user accuracy and 89.0% for producer accuracy). Among the four different classification methods, the combined random forest and object-oriented (RF + OO) model exhibited the highest accuracy (OA = 0.94, Kappa = 0.92), while the support vector machine (SVM) classification method had the lowest accuracy (OA = 0.52, Kappa = 0.31). The total fruit tree plantation area in Aksu City in 2022 was estimated to be 64,000 hectares, with walnut, jujube, pear, and apple trees accounting for 42.5%, 20.6%, 19.3%, and 17.5% of the total fruit tree area, respectively (27,200 hectares, 13,200 hectares, 12,400 hectares, and 11,200 hectares, respectively). The SFS feature optimization and RF + OO-combined classification model algorithm selected in this study effectively mapped the fruit tree planting areas, enabling the estimation of fruit tree planting areas based on remote sensing satellite image data. This approach facilitates accurate fruit tree industry and real-time crop monitoring and provides valuable support for fruit tree planting management by the relevant departments.

Identifying and Monitoring Gardens in Urban Areas Using Aerial and Satellite Imagery

In dry regions, gardens and trees within the urban space are of considerable significance. These gardens are facing harsh weather conditions and environmental stresses; on the other hand, due to the high value of land in urban areas, they are constantly subject to destruction and land use change. Therefore, the identification and monitoring of gardens in urban areas in dry regions and their impact on the ecosystem are the aims of this study. The data utilized are aerial and Sentinel-2 images (2018–2022) for Yazd Township in Iran. Several satellite and aerial image fusion methods were employed and compared. The root mean square error (RMSE) of horizontal shortcut connections (HSC) and color normalization (CN) were the highest compared to other methods with values of 18.37 and 17.5, respectively, while the Ehlers method showed the highest accuracy with a RMSE value of 12.3. The normalized difference vegetation index (NDVI) was then calculated using the images with 15 cm spatial resolution retrieved from the fusion. Aerial images were classified by NDVI and digital surface model (DSM) using object-oriented methods. Different object-oriented classification methods were investigated, including support vector machine (SVM), Bayes, random forest (RF), and k-nearest neighbor (KNN). SVM showed the greatest accuracy with overall accuracy (OA) and kappa of 86.2 and 0.89, respectively, followed by RF with OA and kappa of 83.1 and 0.87, respectively. Separating the gardens using NDVI, DSM, and aerial images from 2018, the images were fused in 2022, and the current status of the gardens and associated changes were classified into completely dried, drying, acceptable, and desirable conditions. It was found that gardens with a small area were more prone to destruction, and 120 buildings were built in the existing gardens in the region during 2018–2022. Moreover, the monitoring of land surface temperature (LST) showed an increase of 14 °C in the areas that were changed from gardens to buildings.