Explore the vast range of titles available.

Very high-resolution satellite imagery (≤5 m resolution) has become available on a spatial and temporal scale appropriate for dynamic wetland management and conservation across large areas. Estuarine wetlands have the potential to be mapped at a detailed habitat scale with a frequency that allows immediate monitoring after storms, in response to human disturbances, and in the face of sea-level rise. Yet mapping requires significant fieldwork to run modern classification algorithms and estuarine environments can be difficult to access and are environmentally sensitive. Recent advances in unoccupied aircraft systems (UAS, or drones), coupled with their increased availability, present a solution. UAS can cover a study site with ultra-high resolution (<5 cm) imagery allowing visual validation. In this study we used UAS imagery to assist training a Support Vector Machine to classify WorldView-3 and RapidEye satellite imagery of the Rachel Carson Reserve in North Carolina, USA. UAS and field-based accuracy assessments were employed for comparison across validation methods. We created and examined an array of indices and layers including texture, NDVI, and a LiDAR DEM. Our results demonstrate classification accuracy on par with previous extensive fieldwork campaigns (93% UAS and 93% field for WorldView-3; 92% UAS and 87% field for RapidEye). Examining change between 2004 and 2017, we found drastic shoreline change but general stability of emergent wetlands. Both WorldView-3 and RapidEye were found to be valuable sources of imagery for habitat classification with the main tradeoff being WorldView’s fine spatial resolution versus RapidEye’s temporal frequency. We conclude that UAS can be highly effective in training and validating satellite imagery.

Deep learning-based segmentation of very high-resolution (VHR) satellite images is a significant task providing valuable information for various geospatial applications, specifically for land use/land cover (LULC) mapping. The segmentation task becomes more challenging with the increasing number and complexity of LULC classes. In this research, we generated a new benchmark dataset from VHR Worldview-3 images for twelve distinct LULC classes of two different geographical locations. We evaluated the performance of different segmentation architectures and encoders to find the best design to create highly accurate LULC maps. Our results showed that the DeepLabv3+ architecture with an ResNeXt50 encoder achieved the best performance for different metric values with an IoU of 89.46%, an F-1 score of 94.35%, a precision of 94.25%, and a recall of 94.49%. This design could be used by other researchers for LULC mapping of similar classes from different satellite images or for different geographical regions. Moreover, our benchmark dataset can be used as a reference for implementing new segmentation models via supervised, semi- or weakly-supervised deep learning models. In addition, our model results can be used for transfer learning and generalizability of different methodologies.

Crop yield monitoring is an important component in agricultural assessment. Multispectral remote sensing instruments onboard space-borne platforms such as Advanced Very High Resolution Radiometer (AVHRR), Moderate Resolution Imaging Spectroradiometer (MODIS), and Visible Infrared Imaging Radiometer Suite (VIIRS) have shown to be useful for efficiently generating timely and synoptic information on the yield status of crops across regional levels. However, the coarse spatial resolution data inherent to these sensors provides little utility at the management level. Recent satellite imagery collection advances toward finer spatial resolution (down to 1 m) alongside increased observational cadence (near daily) implies information on crops obtainable at field and within-field scales to support farming needs is now possible. To test this premise, we focus on assessing the efficiency of multiple satellite sensors, namely WorldView-3, Planet/Dove-Classic, Sentinel-2, and Landsat 8 (through Harmonized Landsat Sentinel-2 (HLS)), and investigate their spatial, spectral (surface reflectance (SR) and vegetation indices (VIs)), and temporal characteristics to estimate corn and soybean yields at sub-field scales within study sites in the US state of Iowa. Precision yield data as referenced to combine harvesters’ GPS systems were used for validation. We show that imagery spatial resolution of 3 m is critical to explaining 100% of the within-field yield variability for corn and soybean. Our simulation results show that moving to coarser resolution data of 10 m, 20 m, and 30 m reduced the explained variability to 86%, 72%, and 59%, respectively. We show that the most important spectral bands explaining yield variability were green (0.560 µm), red-edge (0.726 µm), and near-infrared (NIR - 0.865 µm). Furthermore, the high temporal frequency of Planet and a combination of Sentinel-2/Landsat 8 (HLS) data allowed for optimal date selection for yield map generation. Overall, we observed mixed performance of satellite-derived models with the coefficient of determination (R^2) varying from 0.21 to 0.88 (averaging 0.56) for the 30 m HLS and from 0.09 to 0.77 (averaging 0.30) for 3 m Planet. R^2 was lower for fields with higher yields, suggesting saturation of the satellite-collected reflectance features in those cases. Therefore, other biophysical variables, such as soil moisture and evapotranspiration, at similar fine spatial resolutions are likely needed alongside the optical imagery to fully explain the yields.

High-spatial-resolution images play an important role in land cover classification, and object-based image analysis (OBIA) presents a good method of processing high-spatial-resolution images. Segmentation, as the most important premise of OBIA, significantly affects the image classification and target recognition results. However, scale selection for image segmentation is difficult and complicated for OBIA. The main challenge in image segmentation is the selection of the optimal segmentation parameters and an algorithm that can effectively extract the image information. This paper presents an approach that can effectively select an optimal segmentation scale based on land object average areas. First, 20 different segmentation scales were used for image segmentation. Next, the classification and regression tree model (CART) was used for image classification based on 20 different segmentation results, where four types of features were calculated and used, including image spectral bands value, texture value, vegetation indices, and spatial feature indices, respectively. WorldView-3 images were used as the experimental data to verify the validity of the proposed method for the selection of the optimal segmentation scale parameter. In order to decide the effect of the segmentation scale on the object area level, the average areas of different land objects were estimated based on the classification results. Experiments based on the multi-scale segmentation scale testify to the validity of the land object’s average area-based method for the selection of optimal segmentation scale parameters. The study results indicated that segmentation scales are strongly correlated with an object’s average area, and thus, the optimal segmentation scale of every land object can be obtained. In this regard, we conclude that the area-based segmentation scale selection method is suitable to determine optimal segmentation parameters for different land objects. We hope the segmentation scale selection method used in this study can be further extended and used for different image segmentation algorithms.

Mapping forest types and tree species at regional scales to provide information for ecologists and forest managers is a new challenge for the remote sensing community. Here, we assess the potential of a U‐net convolutional network, a recent deep learning algorithm, to identify and segment (1) natural forests and eucalyptus plantations, and (2) an indicator of forest disturbance, the tree species Cecropia hololeuca, in very high resolution images (0.3 m) from the WorldView‐3 satellite in the Brazilian Atlantic rainforest region. The networks for forest types and Cecropia trees were trained with 7611 and 1568 red‐green‐blue (RGB) images, respectively, and their dense labeled masks. Eighty per cent of the images were used for training and 20% for validation. The U‐net network segmented forest types with an overall accuracy >95% and an intersection over union (IoU) of 0.96. For C. hololeuca, the overall accuracy was 97% and the IoU was 0.86. The predictions were produced over a 1600 km2 region using WorldView‐3 RGB bands pan‐sharpened at 0.3 m. Natural and eucalyptus forests compose 79 and 21% of the region's total forest cover (82 250 ha). Cecropia crowns covered 1% of the natural forest canopy. An index to describe the level of disturbance of the natural forest fragments based on the spatial distribution of Cecropia trees was developed. Our work demonstrates how a deep learning algorithm can support applications such as vegetation, tree species distributions and disturbance mapping on a regional scale. In this paper, we have assessed the potential of a deep learning algorithm, the U‐net model, to identify and segment (1) natural forest and eucalyptus plantation, and (2) a tree species indicator of past forest disturbance (Cecropia hololeuca) using Red‐Green‐Blue WorldView‐3 images at 0.3 m of spatial resolution. The overall accuracies of both forest types and C. hololeuca segmentations were above 95%. The method was therefore used to map forest types and all individuals of C. hololeuca in a 1600 km² region of fragmented Atlantic Forest near São Paulo, Brazil. From the C. hololeuca occurrence and distribution in the fragments, we derived a new disturbance metric. Our results show that this method is very promising for applications such as tree species or vegetation mapping.

As the world population keeps increasing and cultivating more land, the extraction of vegetation conditions using remote sensing is important for monitoring land changes in areas with limited ground observations. Water supply in wetlands directly affects plant growth and biodiversity, which makes monitoring drought an important aspect in such areas. Vegetation Temperature Condition Index (VTCI) which depends on thermal stress and vegetation state, is widely used as an indicator for drought monitoring using satellite data. In this study, using clear-sky Landsat multispectral images, VTCI was derived from Land Surface Temperature (LST) and the Normalized Difference Vegetation Index (NDVI). Derived VTCI was used to observe the drought patterns of the wetlands in Lake Chad between 1999 and 2018. The proportion of vegetation from WorldView-3 images was later introduced to evaluate the methods used. With an overall accuracy exceeding 90% and a kappa coefficient greater than 0.8, these methods accurately acquired vegetation training samples and adaptive thresholds, allowing for accurate estimations of the spatially distributed VTCI. The results obtained present a coherent spatial distribution of VTCI values estimated using LST and NDVI. Most areas during the study period experienced mild drought conditions, though severe cases were often seen around the northern part of the lake. With limited in-situ data in this area, this study presents how VTCI estimations can be developed for drought monitoring using satellite observations. This further shows the usefulness of remote sensing to improve the information about areas that are difficult to access or with poor availability of conventional meteorological data.

Classification of mangrove species using satellite images is important for investigating the spatial distribution of mangroves at community and species levels on local, regional and global scales. Hence, studies of mangrove deforestation and reforestation are imperative to support the conservation of mangrove forests. However, accurate discrimination of mangrove species remains challenging due to many factors such as data resolution, species number and spectral confusion between species. In this study, three different combinations of datasets were designed from Worldview-3 and Radarsat-2 data to classify four mangrove species, Kandelia obovate (KO), Avicennia marina (AM), Acanthus ilicifolius (AI) and Aegiceras corniculatum (AC). Then, the Rotation Forest (RoF) method was employed to classify the four mangrove species. Results indicated the benefits of dual polarimetric SAR data with an improvement of accuracy by 2–3%, which can be useful for more accurate large-scale mapping of mangrove species. Moreover, the difficulty of classifying different mangrove species, in order of increasing difficulty, was identified as KO < AM < AI < AC. Dual polarimetric SAR data are recognized to improve the classification of AI and AC species. Although this improvement is not remarkable, it is consistent for all three methods. The improvement can be particularly important for large-scale mapping of mangrove forest at the species level. These findings also provide useful guidance for future studies using multi-source satellite data for mangrove monitoring and conservation.

National and international regulations enforce monitoring programmes of water quality to guide management actions of inland water ecosystems. Our study evaluates the effect of spectral and spatial resolutions on the estimation of chlorophyll‐a concentrations in mountain lakes, and derives implications for addressing the adjacency effect, which is critical and understudied in small water bodies. Five lakes in Sierra Nevada (Spain) were repeatedly sampled during 2020, 2021, and 2023, and a total of 100 chlorophyll‐a samples with suitable coincident satellite imagery were analyzed. Laboratory‐obtained chlorophyll‐a concentrations were modeled comparing up to 86 spectral indices and bands as predictors from three satellites: Sentinel‐2 (12 bands, 20 m/pixel), Planet (8 bands, 3 m/pixel) and WorldView‐3 (11 bands, 1.24 m/pixel). Our results showed that multivariate models for estimating chlorophyll‐a using spectral indices did not perform significantly better than using bands alone. The best models always had multiple predictors and included green and near‐infrared bands. Models based on Sentinel‐2 and Planet (Radj2 > 0.45) outperformed those of WorldView‐3 (Radj2 ∼ 0.37), confirming that the latter performed worst despite higher spatial resolution. Regarding distance to shoreline, the Planet model showed the most consistent performance, with stable Radj2 values and low RMSE even at 3 m from shore with a high level of accuracy (Radj2 ∼ 0.3; RMSE ∼ 1.15 μg L−1). Data and models are released to facilitate near‐real‐time monitoring of these vulnerable ecosystems, where field sampling is extremely challenging.

The mapping of field boundaries can provide important information for increasing food production and security in agricultural systems across the globe. Remote sensing can provide a viable way to map field boundaries across large geographic extents, yet few studies have used satellite imagery to map boundaries in systems where field sizes are small, heterogeneous, and irregularly shaped. Here we used very-high-resolution WorldView-3 satellite imagery (0.5 m) and a mask region-based convolutional neural network (Mask R-CNN) to delineate smallholder field boundaries in Northeast India. We found that our models had overall moderate accuracy, with average precision values greater than 0.67 and F1 Scores greater than 0.72. We also found that our model performed equally well when applied to another site in India for which no data were used in the calibration step, suggesting that Mask R-CNN may be a generalizable way to map field boundaries at scale. Our results highlight the ability of Mask R-CNN and very-high-resolution imagery to accurately map field boundaries in smallholder systems.

Spatially explicit information on tree species composition is important for both the forest management and conservation sectors. In combination with machine learning algorithms, very high-resolution satellite imagery may provide an effective solution to reduce the need for labor-intensive and time-consuming field-based surveys. In this study, we evaluated the possibility of using multispectral WorldView-3 (WV-3) satellite imagery for the classification of three main tree species (Quercus robur L., Carpinus betulus L., and Alnus glutinosa (L.) Geartn.) in a lowland, mixed deciduous forest in central Croatia. The pixel-based supervised classification was performed using two machine learning algorithms: random forest (RF) and support vector machine (SVM). Additionally, the contribution of gray level cooccurrence matrix (GLCM) texture features from WV-3 imagery in tree species classification was evaluated. Principal component analysis confirmed GLCM variance to be the most significant texture feature. Of the 373 visually interpreted reference polygons, 237 were used as training polygons and 136 were used as validation polygons. The validation results show relatively high overall accuracy (85%) for tree species classification based solely on WV-3 spectral characteristics and the RF classification approach. As expected, an improvement in classification accuracy was achieved by a combination of spectral and textural features. With the additional use of GLCM variance, the overall accuracy improved by 10% and 7% for RF and SVM classification approaches, respectively.