Search

Wetlands play a vital role in regulating the global carbon cycle, providing biodiversity, and reducing flood risks. These functions maintain ecological balance and ensure human well-being. Timely, accurate monitoring of wetlands is essential, not only for conservation efforts, but also for achieving Sustainable Development Goals (SDGs). In this study, we combined Sentinel-1/2 images, terrain data, and field observation data collected in 2020 to better understand wetland distribution. A total of 22 feature variables were extracted from multi-source data, including spectral bands, spectral indices (especially red edge indices), terrain features, and radar features. To avoid high correlations between variables and reduce data redundancy, we selected a subset of features based on recursive feature elimination (RFE) and Pearson correlation analysis methods. We adopted the random forest (RF) method to construct six wetland delineation schemes and incorporated multiple types of characteristic variables. These variables were based on remote sensing image pixels and objects. Combining red-edge features, terrain data, and radar data significantly improved the accuracy of land cover information extracted in low-mountain and hilly areas. Moreover, the accuracy of object-oriented schemes surpassed that of pixel-level methods when applied to wetland classification. Among the three pixel-based schemes, the addition of terrain and radar data increased the overall classification accuracy by 7.26%. In the object-based schemes, the inclusion of radar and terrain data improved classification accuracy by 4.34%. The object-based classification method achieved the best results for swamps, water bodies, and built-up land, with relative accuracies of 96.00%, 90.91%, and 96.67%, respectively. Even higher accuracies were observed in the pixel-based schemes for marshes, forests, and bare land, with relative accuracies of 98.67%, 97.53%, and 80.00%, respectively. This study's methodology can provide valuable reference information for wetland data extraction research and can be applied to a wide range of future research studies. [ABSTRACT FROM AUTHOR]

In this study, the coastal changes in Hersek Lagoon, have occurred in the 5 years (2015 to 2020) were examined. With the Modified Normalised Difference Water Index (MNDWI), the water areas in the lagoon were determined by object-based classification. When the changes are examined on a regional basis, it is seen that there are erosion and accretion areas were observed. Pearson's r value was examined between End Point Rate (EPR) and Linear Regression Rate (LRR) and a high correlation such as r = 0.921 was obtained. The maximum coastal change was observed as 18.74 m/year with EPR and 18.62 m/year with LRR. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. 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 Background Earthquake is one of the most destructive natural disasters, which cause immediate and long-term changes to the river systems. This research aimed to examine the immediate and five-year impacts of the 2015 Ranau Earthquake (6.0 Mw) on river systems in Malaysian state of Sabah, a region of low earthquake hazard. Methods We used object-based classification on Landsat 8 (2014 and 2015) and Sentinel-2A (2020) satellite imageries to derive land cover time series for investigating the impacts on the riparian areas. Results The earthquake removed vegetation in the riparian zones of four rivers, the highest being the Penataran River (69.21 ha). During the immediate impact period (2014–2015), river bar formation occurred in all rivers, with the largest increase occurring in the Kadamaian River (56.97 ha), followed by the Panataran River (54.36 ha), which had no river bar before the earthquake. The river bar of the Kadamaian River continued to increase, whereas the river bar of the Panataran River decreased five years after the earthquake. Land cover transition analysis revealed that 78.39 ha of vegetation, barren land, and river water areas changed to river bars in the Kadamaian riparian area during the immediate impact period. Except for 26.87% of river bars in the Kadamaian riparian area in 2015, most river bars transitioned to other land cover types five years later. During the period of immediate impact, 22.05 ha of vegetation and 10.71 ha of river water were transformed into river bars along the Penataran River. Five years later, except for 16.2 ha, all river bar areas had transitioned to other cover types. Additionally, 17.7 ha of new river bars were formed. This study provides crucial data on post-earthquake land cover changes, particularly river bar formation and changes, for assessing the earthquake impacts on the river systems and supporting impact mitigation.

Rapid urban expansion in Vietnam presents significant management and environmental challenges. This study quantifies urban growth in the Ha Long City area using a time series of six Landsat images acquired from 2000 to 2023. To address the heterogeneity of the urban class, an object-based (OB) image analysis approach was employed. Instead of relying on spectral channels, Principal component analysis (PCA) was utilized during segmentation, followed by classification using the Random Forest (RF) algorithm. For post-classification processing, a logical filter was applied to confirm the classification results at a detailed level, using additional information from the general classification results. Unconfirmed objects were subsequently verified through visual interpretation. The accuracy of the post-classified process results of this study ranges from 83.44% to 96.64% (producer accuracy) and from 83.48% to 91.27% (user accuracy). The results show that the urban area expanded more than four times, with the most significant growth occurring between 2000 and 2005, and between 2015 and 2020. Notably, land reclamation contributed significantly to urban growth. Understanding these trends is crucial for informed urban planning and environmental management in the region.

The influence of spatial resolution on classification accuracy strongly depends on the research object. With regard to unmanned aerial vehicle (UAV)-based weed mapping, contradictory results on the influence of spatial resolution have been attained so far. Thus, this study evaluates the effect of spatial resolution on the classification accuracy of weeds in a soybean field located in Belm, Lower Saxony, Germany. RGB imagery of four spatial resolutions (0.27, 0.55, 1.10, and 2.19 cm ground sampling distance) corresponding to flight altitudes of 10, 20, 40, and 80 m were assessed. Multinomial logistic regression was used to classify the study area, using both pixel- and object-based approaches. Additionally, the flight and processing times were monitored. For the purpose of an accuracy assessment, the producer's, user's, and overall accuracies as well as the F1 scores were computed and analyzed for statistical significance. Furthermore, McNemar's test was conducted to ascertain whether statistically significant differences existed between the classifications. A linear relationship between resolution and accuracy was found, with a diminishing accuracy as the resolution decreased. Pixel-based classification outperformed object-based classification across all the resolutions examined, with statistical significance (p < 0.05) for 10 and 20 m. The overall accuracies of the pixel-based approach ranged from 80 to 93 percent, while the accuracies of the object-based approach ranged from 75 to 87 percent. The most substantial drops in the weed-detection accuracy with regard to altitude occurred between 20 and 40 m for the pixel-based approach and between 10 and 20 m for the object-based approach. While the decline in accuracy was roughly linear as the flight altitude increased, the decrease in the total time required was exponential, providing guidance for the planning of future UAV-based weed-mapping missions. [ABSTRACT FROM AUTHOR]

Background: Earthquake is one of the most destructive natural disasters, which cause immediate and long-term changes to the river systems. This research aimed to examine the immediate and five-year impacts of the 2015 Ranau Earthquake (6.0 Mw) on river systems in Malaysian state of Sabah, a region of low earthquake hazard. Methods: We used object-based classification on Landsat 8 (2014 and 2015) and Sentinel-2A (2020) satellite imageries to derive land cover time series for investigating the impacts on the riparian areas. Results: The earthquake removed vegetation in the riparian zones of four rivers, the highest being the Penataran River (69.21 ha). During the immediate impact period (2014–2015), river bar formation occurred in all rivers, with the largest increase occurring in the Kadamaian River (56.97 ha), followed by the Panataran River (54.36 ha), which had no river bar before the earthquake. The river bar of the Kadamaian River continued to increase, whereas the river bar of the Panataran River decreased five years after the earthquake. Land cover transition analysis revealed that 78.39 ha of vegetation, barren land, and river water areas changed to river bars in the Kadamaian riparian area during the immediate impact period. Except for 26.87% of river bars in the Kadamaian riparian area in 2015, most river bars transitioned to other land cover types five years later. During the period of immediate impact, 22.05 ha of vegetation and 10.71 ha of river water were transformed into river bars along the Penataran River. Five years later, except for 16.2 ha, all river bar areas had transitioned to other cover types. Additionally, 17.7 ha of new river bars were formed. This study provides crucial data on post-earthquake land cover changes, particularly river bar formation and changes, for assessing the earthquake impacts on the river systems and supporting impact mitigation. [ABSTRACT FROM AUTHOR]

As valued members of forest ecosystems, fast-growing tree species are of great importance for protecting natural forests, fulfilling the demand for raw wood material, and preserving biodiversity and ecosystem services. In this regard, multi-temporal monitoring and evaluation of poplar planted areas are essential for decision makers and planners to keep the inventory maps of planted areas up-to-date and track the temporal changes accurately. Using a spectral library, available spectral knowledge can be incorporated into inventory mapping and image classification processes. In this study, in situ spectral measurements of five Populus (four clones and one species) planted sites in Türkiye were collected at three phenological stages (early, mid, and late vegetation) and a novel spectral library was created after completing strict processing stages. Analysis of the spectral reflectances of the Populus species revealed that their spectral properties in the visible region are similar, whereas the discrimination in the near-infrared and shortwave infrared (SWIR) regions was noticeably higher. Two types of applications were conducted to effectively use the spectral library. First, the spectral library was used to validate the poplar class labels of the sites visited during the field campaign. The effectiveness of Worldview-3 imagery with eight SWIR bands was evaluated by pairwise comparison of the spectral curves of the sample fields with those of the spectral library. Second, the spectral library facilitated the extraction of poplar samples from Sentinel-2 imagery in an unvisited region, and a supervised classification process was conducted using the random forest algorithm. The results revealed that the Populus species (Samsun and I-214) could be delineated with high accuracy (>70%) using 10-band Sentinel-2 imagery, and object-based classification outperformed pixel-based classification by approximately 5% for the poplar types. The developed spectral library stands as a valuable asset for studies focused on identifying and classifying Populus species using high-resolution imagery. [ABSTRACT FROM AUTHOR]

Unravelling slow ecosystem migration patterns requires a fundamental understanding of the broad-scale climatic drivers, which are further modulated by fine-scale heterogeneities just outside established ecosystem boundaries. While modern Unoccupied Aerial Vehicle (UAV) remote sensing approaches enable us to monitor local scale ecotone dynamics in unprecedented detail, they are often underutilised as a temporal snapshot of the conditions on site. In this study in the Southern Alps of New Zealand, we demonstrate how the combination of multispectral and thermal data, as well as LiDAR data (2019), supplemented by three decades (1991–2021) of treeline transect data can add great value to field monitoring campaigns by putting seedling regeneration patterns at treeline into a spatially explicit context. Orthorectification and mosaicking of RGB and multispectral imagery produced spatially extensive maps of the subalpine area (~4 ha) with low spatial offset (Craigieburn: 6.14 ± 4.03 cm; Mt Faust: 5.11 ± 2.88 cm, mean ± standard error). The seven multispectral bands enabled a highly detailed delineation of six ground cover classes at treeline. Subalpine shrubs were detected with high accuracy (up to 90%), and a clear identification of the closed forest canopy (Fuscospora cliffortioides, >95%) was achieved. Two thermal imaging flights revealed the effect of existing vegetation classes on ground-level thermal conditions. UAV LiDAR data acquisition at the Craigieburn site allowed us to model vegetation height profiles for ~6000 previously classified objects and calculate annual fine-scale variation in the local solar radiation budget (20 cm resolution). At the heart of the proposed framework, an easy-to-use extrapolation procedure was used for the vegetation monitoring datasets with minimal georeferencing effort. The proposed method can satisfy the rapidly increasing demand for high spatiotemporal resolution mapping and shed further light on current treeline recruitment bottlenecks. This low-budget framework can readily be expanded to other ecotones, allowing us to gain further insights into slow ecotone dynamics in a drastically changing climate. [ABSTRACT FROM AUTHOR]

Investigating the area under cultivation and yield estimation of agricultural products like rice; can greatly ensure food security, analyze the status of agricultural products and, finaly, sustainable development of developing countries. This study used Sentinel-2 satellite images, to estimate the area under cultivation and the yield of rice paddies in Kunduz province, Afghanistan in the 2020 crop year. Using the time series of NDVI index, the phenology stages of rice plants were obtained and the phenology parameters (SoS and EoS) were extracted using the maximum resolution method. Then, object-oriented classification method based on phenology was used to identify and determine the under-cultivated area of rice fields. In this method, three types of data of reflectivity of reflective bands, NDVI vegetation index and phenology parameters were used as auxiliary data. Yield estimation was done using the experimental method of regression analysis between remote sensing plant indices and the data obtained from ground harvesting. Also, the experimental method based on the regression analysis of ground data and distance measurement with the coefficient of determination of 0.86 and the Pearson correlation coefficient of 0.92 showed its high accuracy in estimating the yield of rice fields. The accuracy of the estimated performance in this research was evaluated by comparing the actual performance (field harvest data) in 27 control points. For this purpose, Pearson's correlation test was used. This test showed that there is a positive and very strong relationship between actual performance and estimated performance (P=0.000, N=27 and R²=0.929). [ABSTRACT FROM AUTHOR]

Wetlands play a vital role in regulating the global carbon cycle, providing biodiversity, and reducing flood risks. These functions maintain ecological balance and ensure human well-being. Timely, accurate monitoring of wetlands is essential, not only for conservation efforts, but also for achieving Sustainable Development Goals (SDGs). In this study, we combined Sentinel-1/2 images, terrain data, and field observation data collected in 2020 to better understand wetland distribution. A total of 22 feature variables were extracted from multi-source data, including spectral bands, spectral indices (especially red edge indices), terrain features, and radar features. To avoid high correlations between variables and reduce data redundancy, we selected a subset of features based on recursive feature elimination (RFE) and Pearson correlation analysis methods. We adopted the random forest (RF) method to construct six wetland delineation schemes and incorporated multiple types of characteristic variables. These variables were based on remote sensing image pixels and objects. Combining red-edge features, terrain data, and radar data significantly improved the accuracy of land cover information extracted in low-mountain and hilly areas. Moreover, the accuracy of object-oriented schemes surpassed that of pixel-level methods when applied to wetland classification. Among the three pixel-based schemes, the addition of terrain and radar data increased the overall classification accuracy by 7.26%. In the object-based schemes, the inclusion of radar and terrain data improved classification accuracy by 4.34%. The object-based classification method achieved the best results for swamps, water bodies, and built-up land, with relative accuracies of 96.00%, 90.91%, and 96.67%, respectively. Even higher accuracies were observed in the pixel-based schemes for marshes, forests, and bare land, with relative accuracies of 98.67%, 97.53%, and 80.00%, respectively. This study’s methodology can provide valuable reference information for wetland data extraction research and can be applied to a wide range of future research studies.

Debris-covered glaciers in High Mountain Asia are important indicators of climatic variability. The present study proposed an improved glacier mapping technique based on a TIRS/(RED/SWIR) band ratio that integrates thermal infrared (TIR), visible red, and shortwave infrared (SWIR) reflectance information with slope parameter to map debris-covered areas. The object-based machine learning technique comprising a hybrid feature selection model and a decision tree classifier was adopted to classify the glacierized region. The mapping results stated that the proposed band ratio combined with the slope parameter has better differentiated supraglacial debris from other glacier surfaces in comparison with the existing debris-covered glacier mapping approaches. The resulted debris-covered glacier boundaries were also validated with reference glacier inventories. The supraglacial debris-covered area was mapped with a high user's accuracy of ≈98%. In addition, a high overall classification accuracy in the range of 99.59–99.84% was achieved with the proposed technique that overcomes the challenges of the previous noteworthy studies, confirming that this technique is effective in detecting debris-covered glaciers. [ABSTRACT FROM AUTHOR]

Copyright of Artvin Çoruh Üniversitesi Orman Fakültesi Dergisi is the property of Artvin Coruh University 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.)

Sown biodiverse pastures (SBP) are a pasture system developed in Portugal. Until 2014, farmers were supported in installing and maintaining SBP, but tracking their locations has been lacking. To survey the country, remote sensing tools with machine learning were used. Here, we developed the first algorithm that combines remote sensing data with machine learning algorithms to identify SBP areas. The algorithm combines Landsat-7 and night-light spectral data with terrain and bioclimatic data. Remotely sensed data offer higher spatial resolution compared to bioclimatic data and also cover interannual variability. Gradient-boosted decision trees (XGB) and artificial neural networks (ANN) were the machine learning methods used. The overall classification accuracy, on an independent validation dataset, was 94%, with 82% producer accuracy and 85% user accuracy. The total estimated area of SBP in the Portuguese region of Alentejo region was 1300 km2 in 2013, which is similar to the total known installed area (approximately 1000 km2). The estimated spatial distribution is in accordance with the known distribution at the municipal level. These results are a critical first step towards the future development of remote systems for assessing the state of SBP and for compliance checks of farmer commitments. [ABSTRACT FROM AUTHOR]

ABSTRACTTimely and accurate wetland information is necessary for wetland resource management. Recent advances in machine learning and remote sensing have facilitated cost-effective monitoring of wetlands. However, reliable methods for fine-grained and rapid wetland mapping are still lacking. To address the issue, a wetland sample set with 20 categories for China was collected based on a sampling strategy that combines automatic sample generation and visual interpretation. Simultaneously, a novel multi-stage method for fine-grained wetland classification was proposed, which integrates pixel-based and object-based strategies using ensemble learning algorithms and multi-source remote sensing data. First, a pixel-based ensemble learning algorithm was implemented to classify five rough wetland categories and six non-wetland categories. Second, an object-based ensemble learning approach was designed to separate the water cover in the pixel-based classification results into eight detailed categories. Third, the merged pixel-based and object-based classification results were refined with knowledge-based post-processing procedures to identify 14 fine-grained wetland categories. Results using the Pixel Information Expert Engine (PIE-Engine) cloud platform proved the effectiveness of the proposed wetland classification method. The overall accuracy, kappa, and weighted F1 reached 87.39%, 82.80%, and 86.02%, respectively. The adopted ensemble learning algorithm yielded better performance than classifiers such as CatBoost, random forest, and XGBoost. The incorporation of spectral, texture, shape, topographic, and geographic features from multi-source data contributed to differentiating wetland categories. According to the relative contribution, spectral indexes (NDVI and NDWI), texture features (sum average and contrast), and topographic features (slope and elevation) were identified as important leading predictors for the first-stage pixel-based classification. Shape features (shape index and compactness) and auxiliary features (geographic location) were crucial predictors for the second-stage object-based classification. Compared with other products, our 10-m wetland mapping results for national wetland reserves were rich in detail and fine in categories. Overall, the constructed sample set and developed classification method show promise in laying a foundation for large-scale wetland mapping. The derived wetland maps can provide support for wetland protection and restoration.

Seaweed aquaculture is vital in protecting the marine eco-environment and mitigating climate change. China generates more than half of the world’s total seaweed production. However, despite multiple local studies, accurate and reliable information on broad-scale seaweed farms is still scarce. Using an object-based method to classify 3 m spatial resolution Planet Scope images along offshore China, a total of 129,494 ha of cultured seaweed was identified and delineated with an overall accuracy of 95.70% and a KAPPA index of 0.912, respectively. Then, a seaweed map in offshore China in 2018–2019 was developed. The results provided basic information about seaweed farms in China. The approach reported in this work is accurate and efficient, which can be used to replace the conventional method to obtain the culture seaweed information. This study can be of reference for mapping seaweed on a broader or global scale.

ABSTRACT Sown biodiverse pastures (SBP) are a pasture system developed in Portugal. Until 2014, farmers were supported in installing and maintaining SBP, but tracking their locations has been lacking. To survey the country, remote sensing tools with machine learning were used. Here, we developed the first algorithm that combines remote sensing data with machine learning algorithms to identify SBP areas. The algorithm combines Landsat-7 and night-light spectral data with terrain and bioclimatic data. Remotely sensed data offer higher spatial resolution compared to bioclimatic data and also cover interannual variability. Gradient-boosted decision trees (XGB) and artificial neural networks (ANN) were the machine learning methods used. The overall classification accuracy, on an independent validation dataset, was 94%, with 82% producer accuracy and 85% user accuracy. The total estimated area of SBP in the Portuguese region of Alentejo region was 1300 km2 in 2013, which is similar to the total known installed area (approximately 1000 km2). The estimated spatial distribution is in accordance with the known distribution at the municipal level. These results are a critical first step towards the future development of remote systems for assessing the state of SBP and for compliance checks of farmer commitments.

Buildings are important components of urban areas, and the construction of rooftop photovoltaic systems plays a critical role in the transition to renewable energy generation. With rooftop solar photovoltaics receiving increased attention, the problem of how to estimate rooftop photovoltaics is under discussion; building detection from remote sensing images is one way to address it. In this study, we presented an available approach to estimate a building's rooftop solar photovoltaic potential. A rapid and accurate rooftop extraction method was developed using object-based image classification combining normalized difference vegetation index (NDVI) and digital surface models (DSMs), and a method for the identification of suitable rooftops for solar panel installation by analysing the geographical restrictions was proposed. The approach was validated using six scenes from Beijing that were taken using Chinese Gaofen-2 (GF-2) satellite imagery and Pleiades imagery. A total of 176 roofs in six scenarios were suitable for PV installation, and the estimated photovoltaic panel area was 205,827 m2. The rooftop photovoltaic potential was estimated to total 22,551 GWh. The results indicated that the rooftop photovoltaic potential estimation method performs well. [ABSTRACT FROM AUTHOR]

Land use land cover (LULC) classification using remote sensing images is a valuable resource in various fields such as climate change, urban development, and land degradation monitoring. The city of Madurai in India is known for its diverse geographical elements and rich heritage, which includes the cultural sport of “Jallikattu”: whose main competitor, the zebusare deeply affected by the conversion of their waterbodies and pastures into concrete jungles. Hence, monitoring land degradation is vital in preserving the geography and cultural heritage of the study area, Madurai. The “Landsat 8 Operational Land Imager tier_2 collection_2 Level_2 Surface Reflectance” image was taken for this study. The LULC classification is performed based on the following classes: forest, agriculture, urban, water bodies, uncultivated land, and bare land. The objective of the study is to incorporate auxiliary features to spectral and textural features along with a simple non-iterative clustering (SNIC) segmentation algorithm and implement a boundary-specific two-level learning approach based on support vector machines (SVM) and k nearest neighbors (kNN) classification algorithms. The overall accuracy (OA) of 95.78% and 0.94 Kappa score (K) were obtained using a boundary-specific two-level model augmented with auxiliary feature and SNIC algorithm in comparison to PB, OB, and OBS, which achieve OA (K) of 81% (0.76), 91% (0.89), and 94.42% (0.92), respectively. The results demonstrate a notable enhancement in overall classification accuracy when augmenting the features and refining classification decisions using a boundary-specific two-level learning approach. [ABSTRACT FROM AUTHOR]

Background and Objectives: Natural disturbances caused by canopy gaps play a crucial role in forest dynamic processes and help preserve biodiversity, influence nutrient cycles, and maintain the complex structure of the forests. Analyzing the characteristics of canopy gaps is necessary to improve our understanding of temporal and spatial changes in the forest canopy and plays an important role in the future management of forest ecosystems. This study was conducted to analyze the canopy gap dynamics in plantation coniferous forests in Golestan province over a period of nine years using remote sensing data. Materials and Methods: UAV images were taken and processed in a part of plantation conifer masses of Arab Dagh in 2019. In addition, aerial digital camera images taken in 2013 from the Army's Geographical Organization were received and processed. In the first step, the identification and preparation of the canopy gaps map was done using the object-based classification method. To evaluate the correctness and accuracy of the maps, the centers and boundaries of several canopy gaps were taken using a differential global positioning device, and some were prepared on the orthomosaic image and CHM. In the second step, 1345 lights were extracted from the classified map of aerial digital camera images, and 1058 canopy gaps were extracted from the classified map of the UAV, which had the highest accuracy, and the characteristics of the canopy gaps were obtained at each time point. In the third step, by crossing the classified maps of aerial digital camera and drone images, which had the highest accuracy. The dynamics of the gaps were analyzed by calculating the characteristics of gap formation rate, gap closure rate, gap expansion rate, gap reduction rate, and gap number increase rate. Finally, to statistically analyze the data, first, their normality was checked using the Kolmogorov-Smirnov test in SAS 9.4 statistical software and then the paired t-test was used to compare the averages. Results: The results of the canopy gap dynamics during the 9 years showed that the number and density of the canopy gap decreased. However, the average area canopy gap and the share of the area of the canopy gap in the total area increased significantly. In both periods, 65% of the canopy gap had an area of less than 150 m², and a large canopy gap (larger than 300 m² ) covered the lowest frequency and share of the total area of the canopy gap. The highest rate of changes in the canopy gap source was related to the gap expansion rate (1.09% per year). The gap closure rate is almost equal to the gap reduction rate. The lowest rate of changes in the light is the gap formation rate (0.77% per year). The logarithmic gap number increase rate (GNIR) was negative (-2.6) and in all canopy gap classes, the number of closed canopy gaps per year is more than it is the number of new canopy gaps that are created. Conclusion: With the passage of 9 years, the density of gaps and the number of gaps have decreased and the total surface of gaps has increased significantly. This increase in the total level of the gap can be attributed to the increase in the gap expansion during the period. Because the gap expansion rate is higher than the gap formation rate, the gap closures rate, and the gap reduction rate. In both periods, the most abundant size was related to small holes, which indicates the predominance of small lights in the studied area, which shows the predominance of small gaps in the studied area; small gaps make up most of the dynamics of gaps and close faster than big gaps. [ABSTRACT FROM AUTHOR]

Acacia mearnsii, an invasive alien species, is the main resource identified for the energy transition initiated on Reunion Island. It is, therefore, critical to identify the existent forest stands within the island's large tropical forest area and to determine which of these stands are accessible for logging operations. In this study, a very high-spatial-resolution image was used to map forest (Acacia mearnsii, Acacia heterophylla, Cryptomeria japonica) and non-forest land cover. To identify the accessible forest stands, we developed a geographic information system (GIS) processing chain, accounting for barriers, the distribution of slopes, and the location of forest roads. User-defined parameters, such as the slope threshold and maximal distance to forest roads, allow different scenarios to be explored. The classification yields an overall accuracy of 88% and a Kappa index of 0.86 and highlights the areas occupied by the different types of Acacia. By applying the GIS processing chain for a standard scenario, the results show that only 19% of the initial study area of 637 ha of Acacia mearnsii patches is suitable for exploitation. In conclusion, our results demonstrate how remote sensing (RS) and GIS can be combined to provide valuable tools for forest managers to design management plans for invasive alien forest species. [ABSTRACT FROM AUTHOR]

The study aims to improve the classification and mapping of snow cover over the Himalayan region, which is essential for assessing water availability and understanding hydrological and climatic interactions. The normalized difference snow index (NDSI) is a traditional digital classification method for snow cover mapping. However, it is not always effective in differentiating snow from other features such as water bodies and shadows of mountain hills. In this study, an improved methodology for snow cover mapping was developed using an object-based classification with NDSI and normalized difference water index (NDWI) over segmented objects instead of pixels to separate snow and water with reduced noise. Shepherd segmentation was used to generate spatially homogeneous objects associated with ground cover features. The study focused on the Chandra basin in Himachal Pradesh, India, using an Indian Remote Sensing Satellite (IRS-P6) LISS-III optical image from 30-09-2016. The developed framework was tested using an object-based NDSI classification and further improved with an object-based NDSI-NDWI classification and validated against a manually digitized snow cover map. Validation showed that the object-based NDSI-NDWI classification provided a significant improvement in snow cover mapping compared to traditional NDSI classification, reducing the overestimation of snow-covered areas by up to 6.14%. The developed methodology was executed in the Python environment with efficient computing power. This study demonstrates that an integrated analysis of object-based classification with NDSI and NDWI, can significantly improve snow cover mapping by separating non-snow features. The results of this study show that they have the potential to be extended to larger regions with snow cover. [ABSTRACT FROM AUTHOR]

The influence of spatial resolution on classification accuracy strongly depends on the research object. With regard to unmanned aerial vehicle (UAV)-based weed mapping, contradictory results on the influence of spatial resolution have been attained so far. Thus, this study evaluates the effect of spatial resolution on the classification accuracy of weeds in a soybean field located in Belm, Lower Saxony, Germany. RGB imagery of four spatial resolutions (0.27, 0.55, 1.10, and 2.19 cm ground sampling distance) corresponding to flight altitudes of 10, 20, 40, and 80 m were assessed. Multinomial logistic regression was used to classify the study area, using both pixel- and object-based approaches. Additionally, the flight and processing times were monitored. For the purpose of an accuracy assessment, the producer’s, user’s, and overall accuracies as well as the F1 scores were computed and analyzed for statistical significance. Furthermore, McNemar’s test was conducted to ascertain whether statistically significant differences existed between the classifications. A linear relationship between resolution and accuracy was found, with a diminishing accuracy as the resolution decreased. Pixel-based classification outperformed object-based classification across all the resolutions examined, with statistical significance (p < 0.05) for 10 and 20 m. The overall accuracies of the pixel-based approach ranged from 80 to 93 percent, while the accuracies of the object-based approach ranged from 75 to 87 percent. The most substantial drops in the weed-detection accuracy with regard to altitude occurred between 20 and 40 m for the pixel-based approach and between 10 and 20 m for the object-based approach. While the decline in accuracy was roughly linear as the flight altitude increased, the decrease in the total time required was exponential, providing guidance for the planning of future UAV-based weed-mapping missions.

In recent years, increasing tree diebacks and mortality in some forests, particularly in forest parks, created a need amongst forest managers to find effective methods to gather information about the rate of dieback and mortality and their reasons. High-quality air and space-born remote sensing data has established as an alternative to field surveys for certain inventory tasks. This study used high-quality UltraCam-Xp and UAV drone images from 2016 and 2021 to map tree dieback and mortality in Daland Forest Park, Golestan Province, Iran. High-quality ortho mosaics and Digital Surface Models (DSMs) were generated from UltraCam (2016) and UAV (2021) images. The images were then classified through object-based classification by Nearest Neighbor (NN), Support Vector Machine (SVM), and Bayes algorithms using various input data sets including spectral bands, Canopy Height Model (CHM), vegetation indices, and texture analysis features. Our results indicate that the Bayes algorithm is more precise in mapping tree dieback for the two time steps compared to other algorithms. The best tree dieback map on UltraCam images was obtained using the spectral bands with CHM, texture analysis features, and vegetation indices. This combination resulted in an overall accuracy of 91.20% and a Kappa coefficient of 0.88. It was also found that combining the UAV main bands with CHM and texture features did produce a high-accuracy map with an overall accuracy of 88.46% and a Kappa coefficient of 0.84. Change detection analysis of tree dieback showed that between 2016 and 2021, the number of healthy trees decreased, and the number of gaps and open areas increased in the study area. We conclude that UltraCam and UAV photographs can serve to identify and map tree dieback and dead trees with good accuracies and can hence support forest health monitoring. [ABSTRACT FROM AUTHOR]

The estimation of aboveground biomass (AGB) in agroforestry systems using remote sensing has proliferated in the last decades. Similarly, machine learning is also being used in AGB assessments. This study reviews the applications of remote sensing and machine learning for AGB estimation in agroforestry systems (AFS). A detailed review was conducted using 33 recent papers by extracting and comparing information on agroforestry type, data sources, methodology, and model accuracy. Statistical tests were performed to evaluate the differences in performances. High- and very-high-resolution imageries (less than 2 m) are widely used for AGB assessment because they helped to delineate heterogeneous features of AFS. Object-based image analysis yielded classification accuracy of up to 90 percent in some cases. Random Forest, Stochastic Gradient Boosting, and Support Vector Regression are the most common algorithms used for AGB estimation. However, there are no statistically significant differences in the performance between machine learning and other models. Similarly, scholars incorporated spectral indices with spectral bands, texture, and biophysical variables as covariate categories into AGB estimation models. The study finds no significant differences in results (R-squared) by adding more covariate categories. The accuracy of AGB estimates depends upon multiple factors, such as the spectral and spatial resolution, number and types of covariates, methods for AFS delineation and AGB estimation, and types and sizes of AFS. Despite some of the methodological challenges around measuring understory vegetation, advancements in cloud computing like Google Earth Engine and the availability of high-resolution datasets present opportunities for wider use of remote sensing for biomass estimation of AFS. Remote sensing and machine learning have the potential to estimate aboveground biomass over a large area with high accuracy and contribute to carbon monitoring. [ABSTRACT FROM AUTHOR]

The application of deep learning (DL) improves the accuracy of object-based classification in urban area, but the huge numbers of labelled samples required for training DL models are difficult to obtain. To address that, we propose a novel semi-supervised object-based classification method that combines pseudo-labelling method and consistency regularization method, named as perturbed peer model (PPM). To evaluate the quality of unlabelled object samples, a new object-level joint confidence is designed to assess the confidence of the samples' prediction, which provides guidance for selecting unlabelled object samples in semi-supervised object-based classification. Instead of only using the high-confidence samples as usual, both the high-confidence samples with discriminative power and the low-confidence samples with a large range of structural features are exploited using pseudo-labelling method and consistency regularization method, respectively, facilitating the fusion of the two methods in the proposed PPM. In addition, two types of perturbations, dropout and difference augmentation, are integrated into the model to drive the consistency regularization method as well as to enhance the difference to facilitate the pseudo-labelling method. Experimental results show that the classification accuracy of PPM is better than the widely-used self-training, co-training, noisy-student, unsupervised data augmentation for consistency training, and FreeMatch methods in urban area. [ABSTRACT FROM AUTHOR]

Many leading countries are boosting renewables, especially solar energy, as a major way to mitigate future energy crises and climate change. Particularly, in China, the number and scale of photovoltaic (PV) power stations have grown unprecedentedly in the last decade. There is an urgent need to monitor the PV power development in order to accurately estimate national renewable potentials and understand the ecological impacts. However, there are few efforts towards providing spatially explicit and time-series datasets of PV development at the regional and national scales. To fill the gap, this study proposes an integrated remote sensing approach for PV power stations mapping by combining image segmentation and object-based classification (ISOC) techniques. We took five northwestern provinces of China as an illustration and produced 30-m medium-resolution PV power station distribution maps from 2007 to 2019. Our analysis shows that the total area of PV power stations in the five provinces increased to 722 km 2 in 2019, with producer, user and overall accuracies of 86%, 100% and 93%. Of the 309 PV station clusters (hereafter, PV parks), the top 7% largest ones account for 61% of the total area of PV power stations, indicating that PV power stations in the Northwest tend to be developed in the form of large-scale centralized PV parks. The land used for PV power stations was mainly converted from four land cover types: Gobi Desert, sandy land, sparse grassland, and moderate grassland. The central government policy on facilitating clean energy played a major role in driving the rapid expansion of PV parks across the country. The methodology and results of this study will help policymakers, researchers, and practitioners to develop corresponding industrial standards and environmental regulations to mitigate the potential environmental impacts, and promote more sustainable development of solar energy in China and beyond.

A semi-automated method has been developed for the extraction of land degradation processes using multi sensor data by applying an object-based classification. The object-based approach creates homogenous objects, which is the key component of this classification. The study utilized optical satellite (Landsat-8), microwave (RISAT-1, SAR) and Cartosat-1 digital elevation model (DEM) over Kanpur Dehat district, Uttar Pradesh, and Surendranagar district, Gujarat, India. The objects were created using Shepherd segmentation algorithm. Normalized difference vegetation index (NDVI) was used to classify the degraded and no apparent degradation (NAD) objects based on the three seasons (rabi, summer, and kharif) Landsat-8 bands. Degraded objects were further classified into salinity, forest water erosion, and water logging using brightness index based on Landsat-8, proximity analysis near the river channel using RISAT-1, and low-lying area using DEM, respectively. The digitally generated results were validated with manual digitized desertification status maps (DSM) published by Space Applications Centre, Ahmedabad, India. The overall accuracy and kappa coefficient for Kanpur Dehat and Surendranagar districts were found 84.67%, 0.79 and 72.33%, 0.60, respectively. This study was carried out based on integrated analysis of different satellites (optical, microwave, and DEM). The advantage of newly designed framework offers less chance of mixing and narrowing down of the area for further classification with better accuracy. The developed framework is based on analytical approach, which was tested and implemented in the Python environment with efficient computing power. The study illustrates that the developed approach is independent of climatic-topographic conditions and executed over pilot study sites, which could be extended over larger regions of the land use/land cover for land degradation mapping. [ABSTRACT FROM AUTHOR]

Numerous uses of the hyperspectral remote sensing technology exist for identifying land cover and tracking its evolution. The classification of hyperspectral images must now take into account both spectral and spatial information due to recent advancements and the production of images with high spatial resolution. Convolutional neural networks (CNNs) have much employed in recent years to enhance the classification precision of hyperspectral images. The simultaneous use of spatial feature extraction methods in CNNs has not received significant attention in prior studies. In this study, a novel CNN architecture has been developed for classifying hyperspectral images. The weighted genetic (WG) algorithm is used in the proposed technique to minimize the hyperspectral image's dimensions. The WG algorithm keeps every band in the image and gives each one weight between zero and one based on how much information it contains. Following the expectation maximization (EM) method to the collected features, the segmented objects are then categorized using the CNN algorithm. Three benchmark hyperspectral images, Pavia, DC Mall, and Indiana Pine, were used to assess the proposed approach. The trials' findings demonstrate the proposed approach's superiority over the multilayer perceptron (MLP) algorithm in the Pavia, DC Mall, and Indiana Pine images by 14, 16, and 8% in the overall accuracy parameter, respectively. [ABSTRACT FROM AUTHOR]

Unravelling slow ecosystem migration patterns requires a fundamental understanding of the broad-scale climatic drivers, which are further modulated by fine-scale heterogeneities just outside established ecosystem boundaries. While modern Unoccupied Aerial Vehicle (UAV) remote sensing approaches enable us to monitor local scale ecotone dynamics in unprecedented detail, they are often underutilised as a temporal snapshot of the conditions on site. In this study in the Southern Alps of New Zealand, we demonstrate how the combination of multispectral and thermal data, as well as LiDAR data (2019), supplemented by three decades (1991–2021) of treeline transect data can add great value to field monitoring campaigns by putting seedling regeneration patterns at treeline into a spatially explicit context. Orthorectification and mosaicking of RGB and multispectral imagery produced spatially extensive maps of the subalpine area (~4 ha) with low spatial offset (Craigieburn: 6.14 ± 4.03 cm; Mt Faust: 5.11 ± 2.88 cm, mean ± standard error). The seven multispectral bands enabled a highly detailed delineation of six ground cover classes at treeline. Subalpine shrubs were detected with high accuracy (up to 90%), and a clear identification of the closed forest canopy (Fuscospora cliffortioides, >95%) was achieved. Two thermal imaging flights revealed the effect of existing vegetation classes on ground-level thermal conditions. UAV LiDAR data acquisition at the Craigieburn site allowed us to model vegetation height profiles for ~6000 previously classified objects and calculate annual fine-scale variation in the local solar radiation budget (20 cm resolution). At the heart of the proposed framework, an easy-to-use extrapolation procedure was used for the vegetation monitoring datasets with minimal georeferencing effort. The proposed method can satisfy the rapidly increasing demand for high spatiotemporal resolution mapping and shed further light on current treeline recruitment bottlenecks. This low-budget framework can readily be expanded to other ecotones, allowing us to gain further insights into slow ecotone dynamics in a drastically changing climate.

Mangrove forests, as an essential component of the coastal zones in tropical and subtropical areas, provide a wide range of goods and ecosystem services that play a vital role in ecology. Mangroves are globally threatened, disappearing, and degraded. Consequently, knowledge on mangroves distribution and change is important for effective conservation and making protection policies. Developing remote sensing data and classification methods have proven to be suitable tools for mapping mangrove forests over a regional scale. Here, we scrutinized and compared the performance of pixel-based and object-based methods under Support Vector Machine (SVM) and Random Forest (RF) algorithms in mapping a mangrove ecosystem into four main classes (Mangrove tree, mudflat, water, and sand spit) using resampled and fused Sentinel-2 images. Additionally, landscape metrics were used to identify the differences between spatial patterns obtained from different classification methods. Results showed that pixel-based classifications were influ-enced heavily by the effect of salt and pepper noise, whereas in object-based classifications, boundaries of land use land cover (LULC) polygons were smoother and visually more appealing. Object-based classifications, with an excellent level of kappa, distinguished mudflat and sand spit from each other and from mangrove better than the pixel-based classifications which obtained a fair-to-good level of kappa. RF and SVM performed differently under comparable circumstances. The results of landscape metrics comparison presented that the classification methods can be affected on quantifying area and size metrics. Although the results supported the idea that fused Sentinel images may provide better results in mangrove LULC classification, further research needs to develop and evaluate various image fusion approaches to make use of all Sentinel's fine resolution images. Our results on the mapping of mangrove ecosystems can contribute to the improvement of management and conservation strategies for these ecosystems being impacted by human activities. [ABSTRACT FROM AUTHOR]

Tropical highlands remain a challenging target for remote sensing due to their high heterogeneity of the landscape and frequent cloud cover, causing a shortage of high-quality and reliable comprehensive data on land use and land cover on a local or regional scale. These, however, are urgently needed by local stakeholders and decisionmakers. This applies for example to the Muringato sub-catchment in Nyeri County, Kenya, where acute water problems have been identified to be usually directly related to specific land use and land cover. This article contributes to the understanding of tropical highlands from a remote sensing perspective by examining Sentinel-1, Sentinel-2 and Global Forest Canopy Height Model data from the Global Ecosystem Dynamics Investigation, all provided by the Google Earth Engine. To do so, we assess classifiers derived from these datasets for different land cover types, analyzing the performance of promising candidates identified in the literature, using 2,800 samples extracted from high-resolution image data across Nyeri County. We also propose an object-based classification strategy based on sequential masking. This strategy is adapted to very heterogeneous landscapes by refining image objects after re-evaluating their homogeneity. Small buildings, which constitute a significant part of the settlement structure in the area, are particularly difficult to detect. To improve the recognition of these objects we additionally consider the local contrast of the relevant classifier to identify potential candidates. Evaluating our sample data, we found that especially optical indices like the Sentinel Water Index, the Enhanced Normalized Difference Impervious Surfaces Index or specific Sentinel-2 bands combined with canopy height data are promising for water, built-up or tree cover detection. With these findings, our proposed object-based classification approach is applied to the Muringato sub-catchment as a representative example of the Kenyan tropical highland region. We achieve a classification accuracy of approximately 88% in the Muringato sub-catchment, outperforming existing products available for the study area. The knowledge gained in the study will also be used for future remote sensing-based monitoring of the region. [ABSTRACT FROM AUTHOR]

Seaweed aquaculture is vital in protecting the marine eco-environment and mitigating climate change. China generates more than half of the world's total seaweed production. However, despite multiple local studies, accurate and reliable information on broad-scale seaweed farms is still scarce. Using an object-based method to classify 3 m spatial resolution Planet Scope images along offshore China, a total of 129,494 ha of cultured seaweed was identified and delineated with an overall accuracy of 95.70% and a KAPPA index of 0.912, respectively. Then, a seaweed map in offshore China in 2018–2019 was developed. The results provided basic information about seaweed farms in China. The approach reported in this work is accurate and efficient, which can be used to replace the conventional method to obtain the culture seaweed information. This study can be of reference for mapping seaweed on a broader or global scale. [ABSTRACT FROM AUTHOR]

Buildings are important components of urban areas, and the construction of rooftop photovoltaic systems plays a critical role in the transition to renewable energy generation. With rooftop solar photovoltaics receiving increased attention, the problem of how to estimate rooftop photovoltaics is under discussion; building detection from remote sensing images is one way to address it. In this study, we presented an available approach to estimate a building’s rooftop solar photovoltaic potential. A rapid and accurate rooftop extraction method was developed using object-based image classification combining normalized difference vegetation index (NDVI) and digital surface models (DSMs), and a method for the identification of suitable rooftops for solar panel installation by analysing the geographical restrictions was proposed. The approach was validated using six scenes from Beijing that were taken using Chinese Gaofen-2 (GF-2) satellite imagery and Pleiades imagery. A total of 176 roofs in six scenarios were suitable for PV installation, and the estimated photovoltaic panel area was 205,827 m2. The rooftop photovoltaic potential was estimated to total 22,551 GWh. The results indicated that the rooftop photovoltaic potential estimation method performs well.

This study focuses on the comparison of machine learning algorithms for classifying the mangrove species of Malad creek, Mumbai, India using pixel-based and object-based approaches. As mangrove forests are complex in structure and require high resolution remotely sensed images for classifying them at the species level, traditional classification methods of remote sensing may not be suitable. In order to find an appropriate method, pixel-based random forest and K Nearest Neighbor classifiers and object-based random forest and K Nearest Neighbor classifiers were tested and compared using WorldView – 2 images. In addition, the best resolution RGB images from Google Earth were classified using random forest and K Nearest Neighbor algorithms in object-based approach and compared. The classification results showed that both object-oriented and pixel-based methods could identify the major mangrove species at the community level. However, the performance of object-based random forest classifier was better than other classification approaches in both WorldView-2 and Google Earth images with overall accuracies of 92.53% and 80.72% and kappa coefficients of 0.89 and 0.73. The overall results showed the potential of random forest classifier in object-based method for classifying the mangroves at the species level. [ABSTRACT FROM AUTHOR]

Crop supply and management is a global issue, particularly in the context of global climate change and rising urbanization. Accurate mapping and monitoring of specific crop types are crucial for crop studies. In this study, we proposed: (1) a methodology to map two main winter crops (winter wheat and winter barley) in the northern region of Finistère with high-resolution Sentinel-2 data. Different classification approaches (the hierarchical classification and the classical direct extraction), and classification methods (pixel-based classification (PBC) and object-based classification (OBC)) were performed and evaluated. Subsequently, (2) a further study that involved monitoring the phenology of the winter crops was carried out, based on the previous results. The aim is to understand the temporal behavior from sowing to harvesting, identifying three important phenological statuses (germination, heading, and ripening, including harvesting). Due to the high frequency of precipitation in our study area, crop phenology monitoring was performed using Sentinel-1 C-band SAR backscatter time series data using the Google Earth Engine (GEE) platform. The results of the classification showed that the hierarchical classification achieved a better accuracy when it is compared to the direct extraction, with an overall accuracy of 0.932 and a kappa coefficient of 0.888. Moreover, in the hierarchical classification process, OBC reached a better accuracy in cropland mapping, and PBC was proven more suitable for winter crop extraction. Additionally, in the time series backscatter coefficient of winter wheat, the germination and ripening (harvesting) phases can be identified at VV and VH/VV polarizations, and heading can be identified in both VV and VH polarizations. Secondly, we were able to detect the germination phase of winter barley in VV and VH, ripening with both polarizations and VH/VV, and finally, heading in VV and VH polarizations. [ABSTRACT FROM AUTHOR]

Hyperspectral remote sensing technology has many applications in the fields of land cover classification and examination of their changes. It seems necessary to use both spectral and spatial information in the hyperspectral image classification due to recent developments and the availability of images at higher spatial resolution. In this study, a new approach for object-based classification of hyperspectral images is introduced. In the proposed approach, first nine spatial features, including mean, standard deviation, contrast, homogeneity, correlation, dissimilarity, energy, wavelet transform and Gabor filter, are extracted from the neighboring pixels of the hyperspectral image. Then, the dimensions of the obtained features are reduced using weighted genetic (WG) algorithm. Next, the hierarchical segmentation (HSEG) algorithm is applied to the reduced features. Then, for the objects obtained from segmentation, nine spatial features, area, perimeter, shape index, strength, maximum intensity, minimum intensity, entropy, relation and adjacency, are extracted. Finally, the classification is performed using the multilayer perceptron neural network (MLP) algorithm. The proposed approach was implemented on three hyperspectral images of Indiana Pine, Berlin and Telops. According to the experimental results, the proposed approach is superior to the MLP classification method. This increase in the overall accuracy is about 12% for the Indiana Pine image, about 11% for the Berlin image, and about 8% for the Telops image. [ABSTRACT FROM AUTHOR]

Object-based features like spectral, topographic, and textural are supportive to determine debris-covered glacier classes. The original feature space includes relevant and irrelevant features. The inclusion of all these features increases the complexity and renders the classifier’s performance. Therefore, feature space optimization is requisite for the classification process. Previous studies have shown a rigorous exercise in manually selecting the best combination of features to define the target class and proven to be a time-consuming task. The present study proposed a hybrid feature selection technique to automate the selection of the best suitable features. This study aimed to reduce the classifier’s complexity and enhance the performance of the classification model. Relief-F and Pearson Correlation filter-based feature selection methods ranked features according to the relevance and filtered out irrelevant or less important features based on the defined condition. Later, the hybrid model selected the common features to get an optimal feature set. The proposed hybrid model was tested on Landsat 8 images of debris-covered glaciers in Central Karakoram Range and validated with present glacier inventories. The results showed that the classification accuracy of the proposed hybrid feature selection model with a Decision Tree classifier is 99.82%, which is better than the classification results obtained using other mapping techniques. In addition, the hybrid feature selection technique has sped up the process of classification by reducing the number of features by 77% without compromising the classification accuracy.

In the past decade, it is proven that satellite image classification using an object-based technique is better than the standard pixel-based technique. With the increasing need for classifying multispectral satellite images for urban planning, the accuracy of the classification becomes a significant performance parameter. Object-based classification (OBC) is a technique in which group of pixels having similar spectral properties, called objects, are generated using image segmentation and then these objects are classified based on their attributes. In this paper, the combination of a multiclass AdaBoost algorithm with extra trees classifier (ETC) is proposed with higher prediction accuracy for the OBC of the urban fringe area. The performance of the AdaBoost algorithm is found to be better in terms of classification accuracy than benchmarked SVM and RF classifiers for OBC. These classification methods were applied to IRS-R2 LISS IV data. The AdaBoosted extra trees classifier (ABETC) has demonstrated the highest accuracy with overall accuracy (OA) of 88.47% and a kappa coefficient of 0.85. The computational time of the ABETC is found to be much smaller than the RF algorithm. In detail, the sensitivity of the classifiers was investigated using stratified random sampling with various sample sizes. [ABSTRACT FROM AUTHOR]

One of the main problems in developing countries is unplanned urban growth and land use change. Timely identification of new constructions can be a good solution to mitigate some environmental and social problems. This study examined the possibility of identifying new constructions in urban areas using images from unmanned aerial vehicles (UAV), Google Earth and Sentinel-2. The accuracy of the land cover map obtained using these images was investigated using pixel-based processing methods (maximum likelihood, minimum distance, Mahalanobis, spectral angle mapping (SAM)) and object-based methods (Bayes, support vector machine (SVM), K-nearest-neighbor (KNN), decision tree, random forest). The use of DSM to increase the accuracy of classification of UAV images and the use of NDVI to identify vegetation in Sentinel-2 images were also investigated. The object-based KNN method was found to have the greatest accuracy in classifying UAV images (kappa coefficient = 0.93), and the use of DSM increased the classification accuracy by 4%. Evaluations of the accuracy of Google Earth images showed that KNN was also the best method for preparing a land cover map using these images (kappa coefficient = 0.83). The KNN and SVM methods showed the highest accuracy in preparing land cover maps using Sentinel-2 images (kappa coefficient = 0.87 and 0.85, respectively). The accuracy of classification was not increased when using NDVI due to the small percentage of vegetation cover in the study area. On examining the advantages and disadvantages of the different methods, a novel method for identifying new rural constructions was devised. This method uses only one UAV imaging per year to determine the exact position of urban areas with no constructions and then examines spectral changes in related Sentinel-2 pixels that might indicate new constructions in these areas. On-site observations confirmed the accuracy of this method. [ABSTRACT FROM AUTHOR]

Urban landscapes are rapid changing ecosystems with diverse urban forms that impede the movement of organisms. Therefore, designing and modelling ecological networks to identify biodiversity reservoirs and their corridors are crucial aspects of land management in terms of population persistence and survival. However, the land cover/use maps used for landscape connectivity modelling can lack information in such a highly complex environment. In this context, remote sensing approaches are gaining interest for the development of accurate land cover/use maps. We tested the efficiency of an object-based classification using open-source projects and free images to identify vegetation strata at a very fine scale and evaluated its contribution to landscape connectivity modelling. We compared different spatial and thematic resolutions from existing databases and object-based image analyses in three French cities. Our results suggested that this remote sensing approach produced reliable land cover maps to differentiate artificial areas, tree vegetation and herbaceous vegetation. Land cover maps enhanced with the remote sensing products substantially changed the structural connectivity indices, showing an improvement up to four times the proportion of herbaceous and tree vegetation. In addition, functional connectivity indices evaluated for several forest species were mainly impacted for medium dispersers in quantitative (metrics) and qualitative (corridors) estimations. Thus, the combination of this reproductible remote sensing approach and landscape connectivity modelling at a very fine scale provides new insights into the characterisation of ecological networks for conservation planning.

The Ningaloo Reef, Australia's longest fringing reef, is uniquely positioned in the NW region of the continent, with clear, oligotrophic waters, relatively low human impacts, and a high level of protection through the World Heritage Site and its marine park status. Non-invasive optical sensors, which seamlessly derive bathymetry and bottom reflectance, are ideally suited for mapping and monitoring shallow reefs such as Ningaloo. Using an existing airborne hyperspectral survey, we developed a new, geomorphic layer for the reef for depths down to 20 m, through an object-oriented classification that combines topography and benthic cover. We demonstrate the classification approach using three focus areas in the northern region of the Muiron Islands, the central part around Point Maud, and Gnaraloo Bay in the south. Topographic mapping combined aspect, slope, and depth into 18 classes and, unsurprisingly, allocated much of the area into shallow, flat lagoons, and highlighted narrow, deeper channels that facilitate water circulation. There were five distinct geomorphic classes of coral-algal mosaics in different topographic settings. Our classifications provide a useful baseline for stratifying ecological field surveys, designing monitoring programmes, and assessing reef resilience from current and future threats. [ABSTRACT FROM AUTHOR]

Globally, native semiarid grasslands and savannas have experienced a densification of woody plant species—leading to a multitude of environmental, economic, and cultural changes. These encroached areas are unique in that the diversity of tree species is small, but at the same time the individual species possess diverse phenological responses. The overall goal of this study was to evaluate the ability of very high resolution drone imagery to accurately map species of woody plants encroaching on semiarid grasslands. For a site in the Edwards Plateau ecoregion of central Texas, we used affordable, very high resolution drone imagery to which we applied maximum likelihood (ML), support vector machine (SVM), random forest (RF), and VGG-19 convolutional neural network (CNN) algorithms in combination with pixel-based (with and without post-processing) and object-based (small and large) classification methods. Based on test sample data (n = 1000) the VGG-19 CNN model achieved the highest overall accuracy (96.9%). SVM came in second with an average classification accuracy of 91.2% across all methods, followed by RF (89.7%) and ML (86.8%). Overall, our findings show that RGB drone sensors are indeed capable of providing highly accurate classifications of woody plant species in semiarid landscapes—comparable to and even greater in some regards to those achieved by aerial and drone imagery using hyperspectral sensors in more diverse landscapes. [ABSTRACT FROM AUTHOR]