Producer's Accuracy Research Articles

National Scale Land Cover Classification Using the Semiautomatic High-Quality Reference Sample Generation (HRSG) Method and an Adaptive Supervised Classification Scheme

The advent of new high-performance cloud computing platforms (e.g., Google Earth Engine (GEE)) and freely available satellite data provides a great opportunity for land cover (LC) mapping over large-scale areas. However, the shortage of reliable and sufficient reference samples still hinders large-scale LC classification. Here, selecting Turkey as the case study, we presented a Semi-automatic High-quality Reference Sample Generation (HRSG) method using the publicly available scientific LC products and the linear spectral unmixing analysis to generate high-quality ground samples for the years 1995 and 2020 within the GEE platform. Furthermore, we developed an adaptive random forest classification scheme based on Köppen-Geiger climate zone classification system. Our rationale was related to the fact that large-scale study areas often contain multiple climate zones where the spectral signature of the same LC class may vary within different climate zones that can lead to a poor LC classification accuracy. To have a robust assessment, the generated LC maps were evaluated against independent test datasets. In regard to the proposed sample generation method, it was observed that HRSG can generate high-quality samples independent of the characteristics of scientific LC products. The high overall accuracy of 92% for 2020 and 90% for 1995 and satisfactory results for producer's accuracy (ranging between 83.4% and 99.3%) and user's accuracy (ranging between 86.1% and 99.7%) of nine LC classes demonstrated the effectiveness of the proposed framework. The presented methodologies can be incorporated into future studies related to large scale LC mapping and LC change monitoring studies.

The Status and Influencing Factors of Surface Water Dynamics on the Qinghai-Tibet Plateau During 2000–2020

The Qinghai–Tibet Plateau is rich in water resources with numerous lakes, rivers, and glaciers, and, as a source of many rivers in Central Asia, it is known as the Asian Water Tower. Under global climate change, it is critical to understand the current influencing factors on surface water area in this region. Although there are numerous studies on surface water mapping, they are still limited by temporal/spatial resolution and record length. Moreover, the complicated topographic condition makes it challenging to map the surface water accurately. Here, we proposed an automatic two-step annual surface water classification framework using long time-series Landsat images and topographic information based on the Google Earth Engine (GEE) platform. The results showed that the producer accuracy (PA) and user accuracy (UA) of the surface water map in the Qinghai–Tibet Plateau in 2020 were 99% and 90%, respectively, and the Kappa coefficient reached 0.87. Our dataset showed high consistency with high-resolution images, indicating that the proposed large-scale water mapping method has great application potential. Furthermore, a new annual surface water area dataset on the Qinghai–Tibet Plateau from 2000 to 2020 was generated, and its relationship with climate, vegetation, permafrost, and glacier factors was explored. We found that the mean surface water area was about 59 481 km2, and there was a significant increasing trend (=322 km2/year, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$p &lt; 0.01$ </tex-math></inline-formula> ) during 2000–2020 in the plateau. Greening, warming, and wetting climate conditions contributed to the increase of surface water area. Active layer thickness and permafrost types may be the most related to the decrease of surface water area. This study provides important information for ecological assessment and protection of the plateau and promotes the implementation of sustainable development goals related to surface water resources.

Tree Species Classifications of Urban Forests Using UAV-LiDAR Intensity Frequency Data

The accurate classification of tree species is essential for the sustainable management of forest resources and the effective monitoring of biodiversity. However, a literature review shows that most of the previous unmanned aerial vehicle (UAV) light detection and ranging (LiDAR)-based studies on fine tree species classification have used only limited intensity features, accurately identifying relatively few tree species. To address this gap, this study proposes developing a new intensity feature—intensity frequency—for the LiDAR-based fine classification of eight tree species. Intensity frequency is defined as the number of times a certain intensity value appears in the individual tree crown (ITC) point cloud. In this study, we use UAV laser scanning to obtain LiDAR data from urban forests. Intensity frequency features are constructed based on the extracted intensity information, and a random forest (RF) model is used to classify eight subtropical forest tree species in southeast China. Based on four-point cloud density sampling schemes of 100%, 80%, 50% and 30%, densities of 230 points/m2, 184 points/m2, 115 points/m2 and 69 points/m2 are obtained. These are used to analyze the effect of intensity frequency on tree species classification accuracy under four different point cloud densities. The results are shown as follows. (1) Intensity frequencies of trees are not significantly different for intraspecies (p &gt; 0.05) values and are significantly different for interspecies (p &lt; 0.01) values. (2) The intensity frequency features of LiDAR can be used to classify different tree species with an overall accuracy (OA) of 86.7%. Acer Buergerianum achieves a user accuracy (UA) of over 95% and a producer accuracy (PA) of over 90% for four density conditions. (3) The OA varies slightly under different point cloud densities, but the sum of correct classification trees (SCI) and PA decreases rapidly as the point cloud density decreases, while UA is less affected by density with some stability. (4) The priori feature selected by mean rank (MR) covers the top 10 posterior features selected by RF. These results show that the new intensity frequency feature proposed in this study can be used as a comprehensive and effective intensity feature for the fine classification of tree species.

Using computer vision, image analysis and UAVs for the automatic recognition and counting of common cranes (Grus grus)

Long-term monitoring of wildlife numbers traditionally uses observers, which are frequently inefficient and inaccurate due to their variable experience/training, are costly and difficult to sustain over time. Furthermore, there are other inhibiting factors for wildlife counting, such as: inhabiting inaccessible areas, fear of humans, and nocturnal behavior. There is a need to develop new technologies that will automatically identify and count wild animals in order to determine the appropriate management protocol. In this study, an advanced and accurate method for automatically calculating the number of cranes (Grus grus), using thermal cameras at night and visible light (RGB) cameras during the day onboard unmanned aerial vehicles (UAVs), based on image analysis and computer vision, was developed. The cranes congregate at night in a large communal roost, making it possible to count the birds while they are relatively static and all together. Each bird was counted individually by creating a standardized tool to determine population numbers for management, using image analysis and automatic processing. A dedicated algorithm was developed that aimed to identify the cranes based on their spectral characteristics (typical temperature, shape, size) and to effectively separate the cranes from the typical background. The automatic segmentation and counting of roosting common cranes using UAV nighttime thermal images had an Overall Accuracy (OA) of 91.47%, User's Accuracy (UA) of 99.68%, and Producer's Accuracy (PA) of 91.74%. The computer vision and machine learning algorithm based on the YOLO v3 platform of daytime RGB UAV images of common cranes at the feeding station yielded an overall loss accuracy level of 2.25%, with a mean square error of 1.87, OA of 94.51%, UA of 99.91%, PA of 94.59%. These results are highly encouraging, and although the algorithms were developed for the purpose of counting cranes, they could be adapted for other counting purposes for wildlife management.

Using sUAV imagery to map litter of invasive annual grass in dry environmental conditions

Invasive annual grasses pose a severe threat to drylands of the United States by increasing habitat degradation and the occurrence and severity of wildfires, while simultaneously outcompeting native species. Advances in technology and accessibility of small uncrewed aerial vehicles (sUAV) provide the opportunity for small preserve managers to map and monitor plant invasions in critical habitats for rare and endemic plant species. Many remote sensing techniques rely on the invasive plants' different phenological signals to distinguish them from native plants and habitats. However, invasive annual grasses in the western United States have high variability of interannual productivity and may not green up each year. Therefore, our objective was to use an sUAV (quadcopter drone) to map invasive annual grass regardless of phenological stage in critical Mojave Desert habitat. The study locations were White Dome, a small habitat preserve, and Beehive Dome in Washington County UT, USA. These areas are critical habitats for several endangered and threatened plant species and are covered with sensitive biological soil crusts, making on-the-ground measurements destructive. Using imagery collected with an sUAV we created red, green, blue (RGB) orthomosaics and calculated the Visible Atmospherically Resistant Index (VARI) across these areas. We successfully mapped the litter of invasive annual grasses at one of the two sites. At White Dome, we attained 95.2 % and 84.3 % Producer's and User's Accuracy in mapping invasive annual grasses based on the RGB spectral signature of invasive grass litter. At Beehive Dome, the heterogeneous nature of the edaphic and topographical features made it difficult to accurately map (<20 %) using VARI and RGB alone. Here, we propose plans to increase accuracy in these dryland systems to be able to map invasive annual grasses regardless of year or environmental conditions.

Mapping cashew monocultures in the Western Ghats using optical and radar imagery in Google Earth Engine

Tropical deforestation is increasingly driven by the expansion of agricultural commodity production. Mapping commodity crops is an important step towards monitoring commodity-driven deforestation. Advances in remote sensing technology, such as the availability of high-resolution imagery and the combination of optical and radar imagery have enabled the detection of the tree-like crops which are difficult to distinguish from forest cover. Cashew is an example of a tree-like crop that grows in areas with high forest cover and biodiversity. Cashew is reported to occupy ∼7.1 million ha globally yet mapping it has been constrained by unclear boundaries due to spatial mixing with forests, an indistinct spectral signature, and structural composition that resembles forests. We employed optical, radar, and a combination of the two imagery types to detect and map cashew monocultures in south Maharashtra, India for 2020. We performed a land cover classification on Google Earth Engine using Random Forest, Classification And Regression Trees and Support Vector Machine algorithms. The combination of Sentinel-2 and Sentinel-1 SAR imagery using Random Forest algorithm yielded the highest unbiased overall accuracy (83%) and unbiased producer's and user's accuracies of 71% and 86% respectively for cashew land cover and was considered the best approach. According to our best approach, monoculture cashew plantations occupy 53,350.37 ha of total land area in the Sawantwadi- Dodamarg landscape in India. This study shows that a combination of optical and radar imagery can be used for cashew land cover classification in the Western Ghats, and future studies could modify these methods for cashew mapping in other landscapes. This study contributes to a growing body of literature supporting the use of both optical and radar imagery for detecting tree-like crop cover.

Mapping of small water bodies with integrated spatial information for time series images of optical remote sensing

Small water bodies and their temporal changes are, especially in urban areas, closely related to people’s daily life and they have an impact on the living environment. For small water bodies mapping with optical remote sensing images, it is challenging to establish a balance between reducing incorrect water detection and increasing the integrity of water extraction. For time-series application, the temporal variability of the spectral information is also challenging for the widely used threshold methods, which are frequently solely based on spectral analysis. In this work we propose a spatial information-integrated small water bodies mapping (SWM) method to achieve a complete and accurate extraction and temporal change monitoring of small water bodies in complex urban environments. Our strategy is to make use of the spatial contextual information to account for the indistinguishability of small water bodies in spectral information. The roughness of the water index is calculated to enhance the contrast between water bodies and other thematic classes eventually present in the imagery. The proposed SWM was applied to different water indexes with an automatic threshold determination. We tested the effectiveness of the proposed algorithm using Landsat and Sentinel-2 multispectral data from three different urban environments (Shanghai, Guangzhou, and Wuhan in China) which include a variety of river courses and lakes. Nantan Lake of China is selected as a representative experimental area to test the SWM method by generating the inter- and intra-year water results. Overall accuracy (OA), F1 score (F1), producer’s accuracy (PA), and user’s accuracy (UA) were used to quantitatively evaluate the accuracy of the algorithm. Compared with the four state-of-the-art water detection methods (supervised random forest classification, hierarchical clustering, multi-band threshold, and modified normalized difference water index (MNDWI)), the proposed SWM algorithm achieves better water extraction performance. Small water bodies are found to be extracted more completely and incorrect water extractions are alleviated. The overall accuracy of the SWM algorithm achieves an average of approx. 97% (OA) and 0.95 (F1). The long-time sequence (from 2007 to 2021) and the short-time interval (monthly results of the year 2020) of the water extraction results by the SWM agree well with the ground truth data. The mean absolute area deviations between the water body extraction results of the SWM algorithm and ground truth is significantly smaller than that of the Global Surface Water dataset developed by the European Commission's Joint Research Centre (3.5% vs 49.0% for annual results and 6.0% vs 35.0% for monthly results).

Detection of Ecballium elaterium in hedgerow olive orchards using a low-cost uncrewed aerial vehicle and open-source algorithms.

Ecballium elaterium (common name: squirting cucumber) is an emerging weed problem in hedgerow or superintensive olive groves under no tillage. It colonizes the inter-row area infesting the natural or sown cover crops, and is considered a hard-to-control weed. Research in other woody crops has shown E. elaterium has a patchy distribution, which makes this weed susceptible to design a site-specific control strategy only addressed to E. elaterium patches. Therefore, the aim of this work was to develop a methodology based on the analysis of imagery acquired with an uncrewed aerial vehicle (UAV) to detect and map E. elaterium infestations in hedgerow olive orchards. The study was conducted in two superintensive olive orchards, and the images were taken using a UAV equipped with an RGB sensor. Flights were conducted on two dates: in May, when there were various weeds infesting the orchard, and in September, when E. elaterium was the only infesting weed. UAV-orthomosaics in the first scenario were classified using random forest models, and the orthomosaics from September with E. elaterium as the only weed, were analyzed using an unsupervised algorithm. In both cases, the overall accuracies were over 0.85, and the producer's accuracies for E. elaterium ranged between 0.74 and 1.00. These results allow the design of a site-specific and efficient herbicide control protocol which would represent a step forward in sustainable weed management. The development of these algorithms in free and open-source software fosters their application in small and medium farms. © 2022 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Banana Mapping in Heterogenous Smallholder Farming Systems Using High-Resolution Remote Sensing Imagery and Machine Learning Models with Implications for Banana Bunchy Top Disease Surveillance

Banana (and plantain, Musa spp.), in sub-Saharan Africa (SSA), is predominantly grown as a mixed crop by smallholder farmers in backyards and small farmlands, typically ranging from 0.2 ha to 3 ha. The crop is affected by several pests and diseases, including the invasive banana bunchy top virus (BBTV, genus Babuvirus), which is emerging as a major threat to banana production in SSA. The BBTV outbreak in West Africa was first recorded in the Benin Republic in 2010 and has spread to the adjoining territories of Nigeria and Togo. Regular surveillance, conducted as part of the containment efforts, requires the identification of banana fields for disease assessment. However, small and fragmented production spread across large areas poses complications for identifying all banana farms using conventional field survey methods, which is also time-consuming and expensive. In this study, we developed a remote sensing approach and machine learning (ML) models that can be used to identify banana fields for targeted BBTV surveillance. We used medium-resolution synthetic aperture radar (SAR), Sentinel 2A satellite imagery, and high-resolution RGB and multispectral aerial imagery from an unmanned aerial vehicle (UAV) to develop an operational banana mapping framework by combining the UAV, SAR, and Sentinel 2A data with the Support Vector Machine (SVM) and Random Forest (RF) machine learning algorithms. The ML algorithms performed comparatively well in classifying the land cover, with a mean overall accuracy (OA) of about 93% and a Kappa coefficient (KC) of 0.89 for the UAV data. The model using fused SAR and Sentinel 2A data gave an OA of 90% and KC of 0.86. The user accuracy (UA) and producer accuracy (PA) for the banana class were 83% and 78%, respectively. The BBTV surveillance teams used the banana mapping framework to identify banana fields in the BBTV-affected southwest Ogun state of Nigeria, which helped in detecting 17 sites with BBTV infection. These findings suggest that the prediction of banana and other crops in the heterogeneous smallholder farming systems is feasible, with the precision necessary to guide BBTV surveillance in large areas in SSA.

Wetland mapping based on feature optimization and Google Earth Engine in Zhalong Nature Reserve

Wetlands have very important and irreplaceable ecological service functions in protecting biodiversity and maintaining ecological balance. Due to the unique hydrological characteristics of wetlands, large-scale wetland mapping methods are usually time-consuming, labor intensive, and expensive. With the rise of big data and cloud computing platforms, there are opportunities for long time series and large-scale spatial data processing that improve large-scale wetland mapping. In this study, the Sentinel-1, Sentinel-2, and digital elevation model derived from the Google Earth Engine were used to extract the wetland extent in the Zhalong Nature Reserve based on the Jeffries–Matusita (JM) distance for feature optimization and random forest. Research shows the following: (1) The JM distance for each feature showed that the optical features had the highest separation in all five features and (2) the classification after feature optimization performed best. User accuracy (UA) and producer accuracy (PA) for wetland reached 89.64% and 83.00%, respectively, and overall accuracy reached 90.76%. After feature optimization, PA and UA of wetland were each increased 4.26% and 1.07%, respectively, and the number of features was reduced from 46 to 28. The method used in this study is highly accurate in wetland mapping and can effectively avoid the problem of data redundancy.

Delineation and evaluation of the captive limestone mining area change and its influence on the environment using multispectral satellite images for industrial long-term sustainability

Dynamics in Limestone mining sites are usually subjected to spatiotemporal land cover change, which has a long-term impact on the land and environment. The objectives of this article are mapping demarcation, and transformation assessment of active captive limestone mines and their impact assessment on the environment at the Yerraguntla cement industrial region in YSR Kadapa district, Andhra Pradesh, India from the year 2006–2019 using Remote Sensing & Geographical Information System (RS&GIS). In this research work, first, the Normalized Differential Vegetation Index (NDVI) is computed, second NDVI image is resampled using NDVI threshold values, and the Nearest-Neighbor sampling method uses the QGIS raster calculator, which produces the mines area of 469.92 ha with Sentinel-2A MSI and 555.39 ha with Landsat-8(OLI) which is evaluated with delineated high resolution (∼1m/pixels) Google Earth image (486.47 ha) from Google Earth Pro (freeware) and industry reports (487.10 ha) in 2019. Third active mines are demarcated using NDVI breakpoints. Results found that the limestone Mining area increased by 206.10% from 2006 to 2019, with Producer's Accuracy (PA), User's Accuracy (UA), and Kappa coefficients of 98.82%, 92.79%, and 0.92 in 2019, and 96.74%, 85.17 %t, and 0.82 in 2006. The compatibility between Landsat-8 and Sentinel-2A NDVI images is determined with Pearson's correlation coefficient (PCC) of 0.84 in 2019. In 2019, a linear negative Regression slope was revealed between NDVI & LST with a Correlation coefficient of 0.248, indicating negative environmental influences and vegetation control on LST. This research will aid industry and environmental engineers in comprehending the effects of limestone mine changes on LST and proposing an environmentally acceptable land-environmental management plan for long-term sustainability.

Continuous monitoring of nighttime light changes based on daily NASA's Black Marble product suite

Monitoring nighttime light (NTL) change enables us to quantitatively analyze the dynamic patterns of human activity and socioeconomic features. NASA's Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) atmospheric- and Lunar-BRDF-corrected Black Marble product (VNP46A2) provides daily global nighttime radiances with high temporal consistency. However, timely and continuous monitoring of NTL changes based on the dense daily DNB time series is still lacking. In this study, we proposed a novel Viewing Zenith Angle (VZA) stratified COntinuous monitoring of Land Disturbance (COLD) algorithm (VZA-COLD) to detect NTL change at 15 arc-second spatial resolution with daily updating capability based on NASA's Black Marble products. Specifically, we divided the clear observations into four VZA intervals (0–20°, 20°–40°, 40°–60°, and 0–60°) to mitigate the temporal variation of the NTL data caused by the combined angular effects of viewing geometry and the complex surface conditions (e.g., building heights, vegetation canopy covers, etc.). Single-term harmonic models were continuously estimated for new observations from each VZA interval, and by comparing the model predictions with the actual DNB observations, a unified set of NTL changes can be captured continuously among the different VZA intervals. The final NTL change maps were generated after excluding the consistent dark pixels. Results showed that the VZA-COLD algorithm reduced the DNB data temporal variations caused by disparities among different viewing angles and surface conditions, and successfully detected NTL changes for six globally distributed test sites with an overall accuracy of 99.71%, a user's accuracy of 87.18%, and a producer's accuracy of 68.88% for the NTL change category.

Characterizing ecosystem change in wetlands using dense earth observation time series

Wetlands in drylands are vulnerable to degradation and disappearance due to the combined effects of increasing anthropogenic disturbances and climatic extremes. Such influences may drive non-linear shifts in surface responses that require long-term monitoring approaches for their study. Here, we used a piece-wise regression model to characterize long-term Ecosystem Change Types (ECT) in the surface water and vegetation dynamics of the Inner Niger Delta wetlands in Mali between 2000 and 2019. We also examined the added benefits of using a dense Landsat time series for such segmented trend analysis in comparison with MODIS products that are regularly used for ecosystem trends assessment. Our approach has found statistically significant (p < 0.05) long-term changes in wetland ecosystems, as calculated from Modified Normalized Difference Water Index (MNDWI) and Normalized Difference Vegetation Index (NDVI) image series on both the MODIS and the Landsat scales. The class-specific accuracies of the detected ECTs were evaluated through the validation of temporal trajectories based on the TimeSync logic at selected probability sample locations. Results showed higher user's, producer's, and overall accuracies (OA) when using a dense Landsat time series (OA = 0.89 ± 0.01), outperforming the MOD09A1 time series (OA = 0.37 ± 0.03). Our study provides a robust framework for long-term wetland monitoring that demonstrates the benefits of applying dense Landsat time-series imagery for accurate quantifications of linear and non-linear ecosystem responses in vast highly dynamic floodplain systems. Delivering such an improved assessment, in a spatial resolution that better resolves the characteristics of wetlands ecosystems, has the potential to support the information needs of global conservation and restoration efforts.

Vegetation Mapping with Random Forest Using Sentinel 2 and GLCM Texture Feature—A Case Study for Lousã Region, Portugal

Vegetation mapping requires accurate information to allow its use in applications such as sustainable forest management against the effects of climate change and the threat of wildfires. Remote sensing provides a powerful resource of fundamental data at different spatial resolutions and spectral regions, making it an essential tool for vegetation mapping and biomass management. Due to the ever-increasing availability of free data and software, satellites have been predominantly used to map, analyze, and monitor natural resources for conservation purposes. This study aimed to map vegetation from Sentinel-2 (S2) data in a complex and mixed vegetation cover of the Lousã district in Portugal. We used ten multispectral bands with a spatial resolution of 10 m, and four vegetation indices, including Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Enhanced Vegetation Index (EVI), and Soil Adjusted Vegetation Index (SAVI). After applying principal component analysis (PCA) on the 10 S2A bands, four texture features, including mean (ME), homogeneity (HO), correlation (CO), and entropy (EN), were derived for the first three principal components. Textures were obtained using the Gray-Level Co-Occurrence Matrix (GLCM). As a result, 26 independent variables were extracted from S2. After defining the land use classes using an object-based approach, the Random Forest (RF) classifier was applied. The map accuracy was evaluated by the confusion matrix, using the metrics of overall accuracy (OA), producer accuracy (PA), user accuracy (UA), and kappa coefficient (Kappa). The described classification methodology showed a high OA of 90.5% and kappa of 89% for vegetation mapping. Using GLCM texture features and vegetation indices increased the accuracy by up to 2%; however, classification using GLCM texture features and spectral bands achieved the highest OA (92%), indicating the texture features′ capability in detecting the variability of forest species at stand level. The ME and CO showed the highest contribution to the classification accuracy among the GLCM textures. GNDVI outperformed other vegetation indices in variable importance. Moreover, using only S2A spectral bands, especially bands 11, 12, and 2, showed a high potential to classify the map with an OA of 88%. This study showed that adding at least one GLCM texture feature and at least one vegetation index into the S2A spectral bands may effectively increase the accuracy metrics and tree species discrimination.

Integrating low-altitude drone based-imagery and OBIA for mapping and manage semi natural grassland habitats

Monitoring semi-natural grasslands is difficult and costly because they occur in highly dynamic and extremely complex habitat mosaics. We combined the use of a low-cost unmanned aerial vehicle (UAV) and Structure from Motion (SfM) photogrammetry to acquire high spatial resolution (∼1.5 cm pixel) RGB imagery. After image classification through Object-Based Image Analysis (OBIA), we accurately were able to distinguish three semi-natural grassland types, one of which is a habitat of conservation concern. The use of orthomosaics, digital elevation models (DEMs), and canopy height models (CHMs) yielded excellent overall classification accuracies (>89%) assessed through both remotely validated and ground-truthed points. We identified two layers of woody vegetation with a user's (UA) and producer's (PA) accuracies >73% and three grassland types: closed grassland (UA = 94%; PA = 97%), open grassland habitat (UA = 97%; PA = 93%) and open grasslands with soil erosion (UA = 96%; PA = 98%). The grassland types differed substantially in the cover of vegetation, rocks, stones, and bare soil measured in the field, as well as in the number and relative cover of the habitat diagnostic species. The proposed methodology is highly promising for mapping and monitoring semi-natural grassland of conservation concern in support of tailored management actions.

Confidence intervals for proportion of area estimated from a stratified random sample

Estimating proportion of area from a stratified random sample and reference class labels obtained by ground visit or interpretation of satellite imagery is a common strategy in land cover monitoring. Confidence intervals for the proportion of area are typically estimated using the Wald interval, a procedure that is known to yield less than nominal coverage (i.e., undercoverage) when the proportion of area is small (i.e., comprising 10% or less of the region of interest). The practical implication of undercoverage is that confidence intervals will include the true proportion of area for a smaller percent of samples than is implied by the stated confidence level (e.g., 95%). For simple random sampling, alternate confidence interval methods such as Wilson, Agresti-Coull, and Clopper-Pearson have been developed to remedy the undercoverage of the Wald interval, but these methods are not directly applicable to stratified sampling. In this study, we evaluated the Wald interval and two alternative general confidence interval approaches for the case of two strata. One alternative approach, previously proposed in the literature, is based on estimating effective sample size (neff method), whereas the other approach is a new method based on summing stratum-specific confidence bounds (sumstrat method) computed using one of the alternate confidence interval approaches (Wilson, Agresti-Coull, and Clopper-Pearson) for each stratum. The coverage and length of confidence intervals estimated from the different methods were compared using Monte Carlo simulation applied to a set of populations representing diverse conditions of prevalence of the target class and user's and producer's accuracies of the map used to construct the strata. The commonly applied Wald interval achieved coverage well below the nominal 95% confidence for many of the populations evaluated, and the neff method improved upon this undercoverage in only a few populations. The Wilson sumstrat intervals provided the best coverage as this method achieved close to the nominal 95% coverage or greater for most populations. Length of the Wilson sumstrat intervals was comparable to length of other methods. Further study is needed to determine which confidence interval methods are effective when the number of strata exceeds two.

Development of a Novel Burned-Area Subpixel Mapping (BASM) Workflow for Fire Scar Detection at Subpixel Level

The accurate detection of burned forest area is essential for post-fire management and assessment, and for quantifying carbon budgets. Therefore, it is imperative to map burned areas accurately. Currently, there are few burned-area products around the world. Researchers have mapped burned areas directly at the pixel level that is usually a mixture of burned area and other land cover types. In order to improve the burned area mapping at subpixel level, we proposed a Burned Area Subpixel Mapping (BASM) workflow to map burned areas at the subpixel level. We then applied the workflow to Sentinel 2 data sets to obtain burned area mapping at subpixel level. In this study, the information of true fire scar was provided by the Department of Emergency Management of Hunan Province, China. To validate the accuracy of the BASM workflow for detecting burned areas at the subpixel level, we applied the workflow to the Sentinel 2 image data and then compared the detected burned area at subpixel level with in situ measurements at fifteen fire-scar reference sites located in Hunan Province, China. Results show the proposed method generated successfully burned area at the subpixel level. The methods, especially the BASM-Feature Extraction Rule Based (BASM-FERB) method, could minimize misclassification and effects due to noise more effectively compared with the BASM-Random Forest (BASM-RF), BASM-Backpropagation Neural Net (BASM-BPNN), BASM-Support Vector Machine (BASM-SVM), and BASM-notra methods. We conducted a comparison study among BASM-FERB, BASM-RF, BASM-BPNN, BASM-SVM, and BASM-notra using five accuracy evaluation indices, i.e., overall accuracy (OA), user’s accuracy (UA), producer’s accuracy (PA), intersection over union (IoU), and Kappa coefficient (Kappa). The detection accuracy of burned area at the subpixel level by BASM-FERB’s OA, UA, IoU, and Kappa is 98.11%, 81.72%, 74.32%, and 83.98%, respectively, better than BASM-RF’s, BASM-BPNN’s, BASM-SVM’s, and BASM-notra’s, even though BASM-RF’s and BASM-notra’s average PA is higher than BASM-FERB’s, with 89.97%, 91.36%, and 89.52%, respectively. We conclude that the newly proposed BASM workflow can map burned areas at the subpixel level, providing greater accuracy in regards to the burned area for post-forest fire management and assessment.

An Impervious Surface Spectral Index on Multispectral Imagery Using Visible and Near-Infrared Bands

The accurate mapping of urban impervious surfaces from remote sensing images is crucial for understanding urban land-cover change and addressing impervious-surface-change-related environment issues. To date, the authors of most studies have built indices to map impervious surfaces based on shortwave infrared (SWIR) or thermal infrared (TIR) bands from middle–low-spatial-resolution remote sensing images. However, this limits the use of high-spatial-resolution remote sensing data (e.g., GaoFen-2, Quickbird, and IKONOS). In addition, the separation of bare soil and impervious surfaces has not been effectively solved. In this article, on the basis of the spectra analysis of impervious surface and non-impervious surface (vegetation, water, soil and non-photosynthetic vegetation (NPV)) data acquired from world-recognized spectral libraries and Sentinel-2 MSI images in different regions and seasons, a novel spectral index named the Normalized Impervious Surface Index (NISI) was proposed for extracting impervious area information by using blue, green, red and near-infrared (NIR) bands. We performed comprehensive assessments for the NISI, and the results demonstrated that the NISI provided the best studied performance in separating the soil and impervious surfaces from Sentinel-2 MSI images. Furthermore, regarding impervious surfaces mapping accuracy, the NISI had an overall accuracy (OA) of 89.28% (±0.258), a producer’s accuracy (PA) of 89.76% (±1.754), and a user’s accuracy (UA) of 90.68% (±1.309), which were higher than those of machine learning algorithms, thus supporting the NISI as an effective measurement for urban impervious surfaces mapping and analysis. The results indicate the NISI has a high robustness and a good applicability.

Monthly Burned-Area Mapping using Multi-Sensor Integration of Sentinel-1 and Sentinel-2 and machine learning: Case Study of 2019's fire events in South Sumatra Province, Indonesia

Indonesia has experienced massive historical land and forest fire events, creating transnational environmental and socioeconomic issues. The extent of burned areas (BAs) is one of many indicators that reflect the magnitudes and impacts from fire events, and such information is also used for planning the response and recovery steps after the fire events. This information is usually derived using remote sensing (RS) data. However, the assessment on the performance using available RS data, possible RS data combinations, and existing methods is needed to regularly monitor the BA extent. This study aims to assess the performance from Sentinel-1 synthetic aperture radar polarization (Pol.) and gray-level of co-occurrence matrix (GLCM) textural features and the integration with Sentinel-2 spectral data (Spec.) for the monthly mapping of BA extent using machine learning algorithms, such as random forests (RFs) and extreme gradient boosting (XGB). The study took place in the parts of Ogan Komering Ilir Regency and Banyuasin in South Sumatra Province, Indonesia. This area has complex land-use classes, such as natural vegetation and plantations (pulpwood and oil palm), which were affected by the 2019's fire events. Our study demonstrated that the combination between Pol. from Sentinel-1 and spectral data from Sentinel-2 (Diff.Pol + Spec.) yielded the best classification accuracy with the overall accuracy (OA) values ranging from 91.80% (XGB) to 95.80% (RF) with the producer's accuracy (PA) from 73.33% to 97.66% and user's accuracy (UA) from 76.69% to 89.80% for the BA class. The integration of spectral data using Sentinel-2 reduced the source of misclassification of BAs from false detection from the non-fire-related land-cover conversion, such as logging activities.

SEX DISCRIMINATION OF INDIVIDUAL TREES USING UAV IMAGERY

Abstract. The sex ratio is the proportion of male to female trees, which has a substantial impact on reproductive success and conservation status. Appropriate sex-related differences in dioecious trees commonly result in leading to a robustly structured population. Fieldwork for sex discrimination is time-consuming and labor-required. Benefiting from the unmanned aerial vehicle (UAV) and SfM techniques, the present study aims to detect male and female Caspian poplar (Populus caspica) trees. In March 2021, a heterogeneous forest in Noor city located in Mazandaran province was photographed, then 3D point clouds were extracted from the images using structure from motion algorithm (SfM) to generate an orthomosaic and a point cloud. The field survey was carried out to record the species, sex, and position of the overstory trees which were identifiable on the orthomosaics. A random forest classification algorithm was applied using R software to classify the trees into male and female. By assessing the producer's accuracy, user's accuracy, and overall accuracy, the classification accuracy for identified trees was computed using 10-fold cross-validation. The results showed an accuracy of 83% for identifying Caspian poplar trees and 52% accuracy for Sex discrimination. Overall, our effort to evaluate sex discrimination of dioecious trees using UAV imagery represents a promising preliminary step in forest data collection.