Multispectral Research Articles

Remote sensing for estimating genetic parameters of biomass accumulation and modeling stability of growth curves in alfalfa.

Multi-spectral imaging by unoccupied aerial vehicles provides a non-destructive, high throughput approach to measuring biomass accumulation over successive alfalfa (Medicago sativa L. subsp. sativa) harvests. Information from estimated growth curves can be used to infer harvest biomass and to gain insights into the relationship between growth dynamics and forage biomass stability across cuttings and years. In this study, multi-spectral imaging and several common vegetation indices were used to estimate genetic parameters and model growth of alfalfa cultivars to determine the longitudinal relationship between vegetation indices and forage biomass. Results showed moderate heritability for vegetation indices, with median plot level heritability ranging from 0.11-0.64, across multiple cuttings in three trials planted in Ithaca, NY, and Las Cruces, NM. Genetic correlations between the normalized difference vegetation index and forage biomass were moderate to high across trials, cuttings, and the timing of multi-spectral image capture. To evaluate the relationship between growth parameters and forage biomass stability across cuttings and environmental conditions, random regression modeling approaches were used to estimate the growth parameters of cultivars for each cutting and the variance in growth was compared to the variance in genetic estimates of forage biomass yield across cuttings. These analyses revealed high correspondence between stability in growth parameters and stability of forage yield. The results of this study indicate that vegetation indices are effective at modeling genetic components of biomass accumulation, presenting opportunities for more efficient screening of cultivars and new longitudinal modeling approaches that can provide insights into temporal factors influencing cultivar stability.

Comparative Analysis of Machine Learning Techniques and Data Sources for Dead Tree Detection: What Is the Best Way to Go?

In Central Europe, the extent of bark beetle infestation in spruce stands due to prolonged high temperatures and drought has created large areas of dead trees, which are difficult to monitor by ground surveys. Remote sensing is the only possibility for the assessment of the extent of the dead tree areas. Several options exist for mapping individual dead trees, including different sources and different processing techniques. Satellite images, aerial images, and images from UAVs can be used as sources. Machine and deep learning techniques are included in the processing techniques, although models are often presented without proper realistic validation.This paper compares methods of monitoring dead tree areas using three data sources: multispectral aerial imagery, multispectral PlanetScope satellite imagery, and multispectral Sentinel-2 imagery, as well as two processing methods. The classification methods used are Random Forest (RF) and neural network (NN) in two modalities: pixel- and object-based. In total, 12 combinations are presented. The results were evaluated using two types of reference data: accuracy of model on validation data and accuracy on vector-format semi-automatic classification polygons created by a human evaluator, referred to as real Ground Truth. The aerial imagery was found to have the highest model accuracy, with the CNN model achieving up to 98% with object classification. A higher classification accuracy for satellite imagery was achieved by combining pixel classification and the RF model (87% accuracy for Sentinel-2). For PlanetScope Imagery, the best result was 89%, using a combination of CNN and object-based classifications. A comparison with the Ground Truth showed a decrease in the classification accuracy of the aerial imagery to 89% and the classification accuracy of the satellite imagery to around 70%. In conclusion, aerial imagery is the most effective tool for monitoring bark beetle calamity in terms of precision and accuracy, but satellite imagery has the advantage of fast availability and shorter data processing time, together with larger coverage areas.

Evaluating the utility of combining high resolution thermal, multispectral and 3D imagery from unmanned aerial vehicles to monitor water stress in vineyards

PurposeHigh resolution imagery from unmanned aerial vehicles (UAVs) has been established as an important source of information to perform precise irrigation practices, notably relevant for high value crops often present in semi-arid regions such as vineyards. Many studies have shown the utility of thermal infrared (TIR) sensors to estimate canopy temperature to inform on vine physiological status, while visible-near infrared (VNIR) imagery and 3D point clouds derived from red–green–blue (RGB) photogrammetry have also shown great promise to better monitor within-field canopy traits to support agronomic practices. Indeed, grapevines react to water stress through a series of physiological and growth responses, which may occur at different spatio-temporal scales. As such, this study aimed to evaluate the application of TIR, VNIR and RGB sensors onboard UAVs to track vine water stress over various phenological periods in an experimental vineyard imposed with three different irrigation regimes.MethodsA total of twelve UAV overpasses were performed in 2022 and 2023 where in situ physiological proxies, such as stomatal conductance (gs), leaf (Ψleaf) and stem (Ψstem) water potential, and canopy traits, such as LAI, were collected during each UAV overpass. Linear and non-linear models were trained and evaluated against in-situ measurements.ResultsResults revealed the importance of TIR variables to estimate physiological proxies (gs, Ψleaf, Ψstem) while VNIR and 3D variables were critical to estimate LAI. Both VNIR and 3D variables were largely uncorrelated to water stress proxies and demonstrated less importance in the trained empirical models. However, models using all three variable types (TIR, VNIR, 3D) were consistently the most effective to track water stress, highlighting the advantage of combining vine characteristics related to physiology, structure and growth to monitor vegetation water status throughout the vine growth period.ConclusionThis study highlights the utility of combining such UAV-based variables to establish empirical models that correlated well with field-level water stress proxies, demonstrating large potential to support agronomic practices or even to be ingested in physically-based models to estimate vine water demand and transpiration.

Monitoring invasive exotic grass species in ecological restoration areas of the Brazilian savanna using UAV images

Identifying and monitoring invasive exotic grasses (IEG) is critical for the ecological restoration of grasslands and savannas, as they are the main barrier to the successful recovery of native grasslands and savannas. The integration of high-resolution remote sensing data, acquired through UAVs (Unmanned Aerial Vehicles), with machine learning algorithms is advancing restoration monitoring. The present study aimed to estimate IEG cover and identify plots with different invasive species dominance in ecological restoration areas in the Brazilian savanna. For ground truth, species cover estimates were carried out in plots through point-line intercept sampling. Then, the areas were classified according to the dominance of each invasive species (>40% vegetation cover) or of a mix of native species. A multispectral camera onboard a UAV was used to acquire images in the visible to near-infrared spectrum. From the images, vegetation indices and texture metrics were derived as predictor variables. The Random Forest (RF) algorithm was used to estimate the percentage of invasive species cover and to classify plots in terms of species dominance. The final RF regression for invasive species cover percentage presented an R2 of 0.71 and selected the blue band, NIR and Ratio Vegetation Index (RVI) as the most important variables. The overall accuracy of plot classification according to species dominance was 84%. The most prominent predictors were the Green Chlorophyll Index (GCI), the atmospherically resistant vegetation index (ARVI), and the RVI. The structural and photosynthetic characteristics of exotic and native species influenced the spectral responses. In conclusion, multispectral images acquired with UAV can be used to estimate the proportion of invasion in restoration sites and to map areas dominated by different invasive grass species in grasslands and savannas. This is a useful tool for evaluating restoration success and can help indicate areas that require management interventions.

Unveiling sequential layered heterogeneity in multi-spectral transmission images clustering through iterative terrace compression with adaptive neighborhoods analysis

Multi-spectral transmission imaging looks forward to an early breast cancer screening with cost-effectiveness, safety, and ease of use. However, the biological tissue of the breast owns scattering and strong absorption properties, resulting in transmission images with a low signal-to-noise ratio and prior investigation focused on detection heterogeneity within a single layer, but the different depths in heterogeneity due to the spherical shape of the breast causing the challenges. Accurately detecting heterogeneity in different layers is crucial due to low contrast, veiling layers, and unclear boundaries, which can be difficult to identify in clustering and segmentation. The breast heterogeneity identification can be handled by combining image processing techniques; nevertheless, considering labeling limits and data accessibility, the clustering algorithm provides an acceptable substitute. Therefore, the paper proposes a novel methodology integrating the iterative terrace compression method with adaptive neighborhoods analysis to identify sequential multi-layered heterogeneity and enhance the clustering of multi-spectral transmission images. Our experimental setup involved the collection of low grayscale images across six wavelengths, followed by advanced image processing techniques, including frame accumulation to improve image signal-to-noise ratio and then polynomial surface fitting to eliminate trend items from uneven light. After that, iterative terrace compression with adaptive neighborhoods analysis is applied to reduce redundancy and unveil heterogeneity in different layers and window functions to remove unnecessary gray information. Finally, clustering combined with pseudo-color is used for clustering analysis and visual representation for aiding in heterogeneity detection. Results indicate a significant improvement in detection metrics, with our method outpacing existing techniques regarding the Dice coefficient, F1 score, and Jaccard. This innovative approach not only enhances the characterization of breast tissue heterogeneities in different layers but also promises practical clinical applications in breast cancer screening.

Yield Prediction Models for Rice Varieties Using UAV Multispectral Imagery in the Amazon Lowlands of Peru

Rice is cataloged as one of the most widely cultivated crops globally, providing food for a large proportion of the global population. Integrating Geographic Information Systems (GISs), such as unmanned aerial vehicles (UAVs), into agricultural practices offers numerous benefits. UAVs, equipped with imaging sensors and geolocation technology, enable precise crop monitoring and management, enhancing yield and efficiency. However, Peru lacks sufficient experience with the application of these technologies, making them somewhat unfamiliar in the context of modern agriculture. In this study, we conducted experiments involving four distinct rice varieties (n = 24) at various stages of growth to predict yield using vegetation indices (VIs). A total of nine VIs (NDVI, GNDVI, ReCL, CIgreen, MCARI, SAVI, CVI, LCI, and EVI) were assessed across four dates: 88, 103, 116, and 130 days after sowing (DAS). Pearson correlation analysis, principal component analysis (PCA), and multiple linear regression were used to build prediction models. The results showed a general prediction model (including all the varieties) with the best performance at 130 days after sowing (DAS) using NDVI, EVI, and SAVI, with a coefficient of determination (adjusted-R2 = 0.43). The prediction models by variety showed the best performance for Esperanza at 88 DAS (adjusted-R2 = 0.94) using EVI as the vegetation index. The other varieties showed their best performance using different indices at different times: Capirona (LCI and CIgreen, 130 DAS, adjusted-R2 = 0.62); Conquista Certificada (MCARI, 116 DAS, R2 = 0.52); and Conquista Registrada (CVI and LCI, 116 DAS, adjusted-R2 = 0.79). These results provide critical information for optimizing rice crop management and support the use of unmanned aerial vehicles (UAVs) to inform timely decision making and mitigate yield losses in Peruvian agriculture.

Geospatial Mapping and Detection of Ferrous, Iron Oxides, and Clay Minerals in District Mohmand, Pakistan

The study focuses on the utilization of remote sensing techniques to effectively identify and detect ferrous,iron oxides, and clay minerals in Mohmand district, Pakistan, using LANDSAT 8 multispectral images. This studyfocuses on the increasing demand and importance of these minerals in mining and commercial activities. Mineralexploration in Mohmand district, utilizing remote sensing technology to identify mineral compositions using the bandratio is done. This technique allows for a more focused and precise approach to exploration and extraction techniques.Cloud-free LANDSAT 8 images with minimal vegetation cover were utilized for the analysis. The band ratio approachwas utilized to identify areas exhibiting diverse mineral compositions. The study highlights the effectiveness of thesuggested methodology in mapping and detecting ferrous, iron oxides, and clay minerals, indicating the significantpotential of remote sensing for mineral exploration. The results highlight the importance of developing distributionmaps to support more efficient methods for mining and mineral exploration. The study contributes to a more focusedand efficient assessment of mineral resources and extraction techniques in the Mohmand district and similar geologicalterrains, offering stakeholders a valuable tool for informed decision-making in mineral exploration and exploitationefforts.

Monitoring of parasite Orobanche cumana using Vis-NIR hyperspectral imaging combining with physio-biochemical parameterson host crop Helianthus annuus.

This study provided a non-destructive detection method with Vis-NIR hyperspectral imaging combining with physio-biochemical parameters in Helianthus annuus in response to Orobanche cumana infection that took insights into the monitoring of sunflower weed. Sunflower broomrape (Orobanche cumana Wallr.) is an obligate weed that attaches to the host roots of sunflower (Helianthus annuus L.) leading to a significant reduction in yield worldwide. The emergence of O. cumana shoots after its underground life-cycle causes irreversible damage to the crop. In this study, a fast visual, non-invasive and precise method for monitoring changes in spectral characteristics using visible and near-infrared (Vis-NIR) hyperspectral imaging (HSI) was developed. By combining the bands sensitive to antioxidant enzymes (SOD, GR), non-antioxidant enzymes (GSH, GSH + GSSG), MDA, ROS (O2-, OH-), PAL, and PPO activities obtained from the host leaves, we sought to establish an accurate means of assessing these changes and conducted imaging acquisition using hyperspectral cameras from both infested and non-infested sunflower cultivars, followed by physio-biochemical parameters measurement as well as analyzed the expression of defense related genes. Extreme learning machine (ELM) and convolutional neural network (CNN) models using 3-band images were built to classify infected or non-infected plants in three sunflower cultivars, achieving accuracies of 95.83% and 95.83% for the discrimination of infestation as well as 97.92% and 95.83% of varieties, respectively, indicating the potential of multi-spectral imaging systems for early detection of O. cumana in weed management.

Capability of space borne multispectral image for detecting discoloration in optically complex coastal waters

Coastal pollutants, from harmful algal blooms, sewage and industrial discharges, pose severe risks to marine ecosystems and public health. Recently, Promenade Beach in Puducherry, Southeast-India, experienced reddish-brown water discoloration, suspected to result from either algal blooms or suspended matter. This study monitored the spatial extent and characteristics of the discoloration using Sentinel-2 satellite images from September to November 2023, with field observations and laboratory analyses. Analyses included measurements of chlorophyll-a (Chl-a), Total Suspended Matter (TSM), and the Normalized Difference Chlorophyll Index (NDCI) to differentiate between algal blooms and other pollutants. The satellite data indicated extents of discoloration, with high TSM concentrations (>45 g/m3) and negative NDCI values suggesting absence of algal blooms. No mortality of aquatic organisms was observed during this discoloration, indicating no deleterious impact on aquatic life. This approach highlights the importance of combining satellite technology with field data for effective coastal pollution monitoring, essential for protecting marine ecosystems.

Estimation of macro and micronutrient concentrations in ‘valencia’ orange leaves at different phenological stages using multispectral image analysis and multiple regression

ABSTRACT This study aimed at estimating the macro- and micronutrient concentrations in leaves of Valencia oranges (Citrus sinensis [L.] Osbeck) through multiple regression analysis using multispectral images and vegetation indices (VIs) selected through the stepwise regression method. The data were collected in a commercial orchard of Valencia oranges in El Barretal, Tamaulipas, Mexico. The leaf samples were analysed in a laboratory to determine the concentrations of N, P, K, Ca, Mg, Cu, Fe, Mn, and Zn using traditional chemical methods; the relative chlorophyll values were obtained using a chlorophyll metre (SPAD502 Plus). Multi-spectral images of the tree canopy were acquired using a UAV equipped with a multispectral camera with five wavelengths (blue, green, red, red edge, and near-infrared); based on these data, 85 VIs were calculated. To select the predictor variables that were most relevant for the model, 90 candidate variables were divided into three groups with 30 VIs grouped by nutrients based on the highest and lowest absolute values found in the correlation matrix. Heteroscedasticity and autocorrelation were also assessed through the Breusch-Pagan and Durbin-Watson tests, respectively. The selected variables were used in multiple regression analysis. The resulting models were validated by mean absolute error (MAE), root-mean-square error (RMSE), mean absolute percentage error (MAPE), and coefficient of determination ( R 2 ). The prediction models showed satisfactory results, with values R 2 between 0.79 and 0.95 and relatively low (<10) MAE and RMSE for all nutrients, except Fe ( < 30 ) in all phenological stages; MAPE values were lower than 0.5% for all nutrients. This study showed that multispectral imaging combined with multiple regression analysis effectively predicts nutrient levels in the leaves of Valencia oranges in various phenological stages. This study presents a new perspective on agricultural systems, offering an effective alternative to assess the nutritional conditions of crops.

Impurity Level-Induced Broadband Photoelectric Response in Wide-Bandgap Semiconductor SrSnO3.

Broadband spectrum detectors exhibit great promise in fields such as multispectral imaging and optical communications. Despite significant progress, challenges like materials instability in such devices, complex manufacturing process, and high cost still hinder their further application. Here, we present a method that achieves broadband spectral detection by impurity-level in SrSnO3. We report over 500 mA/W photoresponsivity at 275 nm (ultraviolet C solar-bind) and 367 nm (ultraviolet A) and ∼60 mA/W photoresponsivity at 532 and 700 nm (visible) with a voltage bias of -5 V. Further transport and photoluminescence results reveal a new phase transition at 88 K, which would significantly affect the impurity level of the La-doped SrSnO3 film, indicating that the broadband response attributes to the impurity levels and mutual interactions. Additionally, the photodetector demonstrates excellent robustness and stability under repeated tests and prolonged exposure in air. These findings show the potential of SrSnO3 as a material for photodetectors and propose a method to achieve broadband spectrum detection, creating new possibility for the development of single-phase, low-cost, simple structure, and high-efficiency photodetectors.

Improving Radiometric Block Adjustment for UAV Multispectral Imagery under Variable Illumination Conditions

Unmanned aerial vehicles (UAVs) equipped with multispectral cameras offer great potential for applications in precision agriculture. A critical challenge that limits the deployment of this technology is the varying ambient illumination caused by cloud movement. Rapidly changing solar irradiance primarily affects the radiometric calibration process, resulting in reflectance distortion and heterogeneity in the final generated orthomosaic. In this study, we optimized the radiometric block adjustment (RBA) method, which corrects for changing illumination by comparing adjacent images and from incidental observations of reference panels to produce accurate and uniform reflectance orthomosaics regardless of variable illumination. The radiometric accuracy and uniformity of the generated orthomosaic could be enhanced by improving the weights of the information from the reference panels and by reducing the number of tie points between adjacent images. Furthermore, especially for crop monitoring, we proposed the RBA-Plant method, which extracts tie points solely from vegetation areas, to further improve the accuracy and homogeneity of the orthomosaic for the vegetation areas. To validate the effectiveness of the optimization techniques and the proposed RBA-Plant method, visual and quantitative assessments were conducted on a UAV-image dataset collected under fluctuating solar irradiance conditions. The results demonstrated that the optimized RBA and RBA-Plant methods outperformed the current empirical line method (ELM) and sensor-corrected approaches, showing significant improvements in both radiometric accuracy and homogeneity. Specifically, the average root mean square error (RMSE) decreased from 0.084 acquired by the ELM to 0.047, and the average coefficient of variation (CV) decreased from 24% (ELM) to 10.6%. Furthermore, the orthomosaic generated by the RBA-Plant method achieved the lowest RMSE and CV values, 0.039 and 6.8%, respectively, indicating the highest accuracy and best uniformity. In summary, although UAVs typically incorporate lighting sensors for illumination correction, this research offers different methods for improving uniformity and obtaining more accurate reflectance values from orthomosaics.

Classification of melanocytic lesions using direct illumination multispectral imaging

With rising melanoma incidence and mortality, early detection and surgical removal of primary lesions is essential. Multispectral imaging is a new, non-invasive technique that can facilitate skin cancer detection by measuring the reflectance spectra of biological tissues. Currently, incident illumination allows little light to be reflected from deeper skin layers due to high surface reflectance. A pilot study was conducted at the University Hospital Basel to evaluate, whether multispectral imaging with direct light coupling could extract more information from deeper skin layers for more accurate dignity classification of melanocytic lesions. 27 suspicious pigmented lesions from 23 patients were included (6 melanomas, 6 dysplastic nevi, 12 melanocytic nevi, 3 other). Lesions were imaged before excision using a prototype snapshot mosaic multispectral camera with incident and direct illumination with subsequent dignity classification by a pre-trained multispectral image analysis model. Using incident light, a sensitivity of 83.3% and a specificity of 58.8% were achieved compared to dignity as determined by histopathological examination. Direct light coupling resulted in a superior sensitivity of 100% and specificity of 82.4%. Convolutional neural network classification of corresponding red, green, and blue lesion images resulted in 16.7% lower sensitivity (83.3%, 5/6 malignant lesions detected) and 20.9% lower specificity (61.5%) compared to direct light coupling with multispectral image classification. Our results show that incorporating direct light multispectral imaging into the melanoma detection process could potentially increase the accuracy of dignity classification. This newly evaluated illumination method could improve multispectral applications in skin cancer detection. Further larger studies are needed to validate the camera prototype.

Kernel-guided injection deep network for blind fusion of multispectral and panchromatic images

Deep learning (DL)-based pansharpening methods show advantages in generating a high-resolution multispectral image (MS) by fusing low-resolution MS and high-resolution panchromatic (PAN) images. However, most current research only considers a single fixed kernel in the training process, thus they may fail to handle unknown degradations by using a single model for testing, i.e., blind pansharpening. Consequently, poor performance will occur when encountering the mismatched degradation problem. Therefore, building a single network that can tackle blind pansharpening is more realistic and challenging. To this end, we design an end-to-end blind pansharpening network composed of a kernel estimation sub-network and a fusion sub-network, named BPNet. In particular, different from existing DL-based methods, we control injected details by utilizing prior degradation information produced by kernel estimation sub-network, thus it can adapt to different types of degradation. Besides, we design an effective fusion sub-network with a strong interpretability, which injects details of PAN image into MS image by a learnable injection matrix. Especially, the estimated kernel that indicates the blur level of MS image is used to update the learnable injection matrix. To preserve important features well in the deep network, channel-Transformer is further utilized as a skip-connection in the fusion sub-network. With the combination of kernel estimation and fusion sub-networks, the proposed BPNet has great advantages in complex degradation situations, as the network’s adaptability to diverse unknown degradations is enhanced. Extensive experiments on simulated and real datasets demonstrate that BPNet outperforms other state-of-the-art methods in terms of visual results and objective quality analysis.

Anti Face Spoofing System

Face spoofing, the act of using deceptive techniques such as printed photos or digital images to deceive facial recognition systems, poses a significant threat to the security of various applications, including biometric authentication and access control systems. This paper presents a concise yet effective approach to address the challenge of anti-face spoofing using Python within a limited codebase of 50 lines. The proposed solution leverages a combination of image processing techniques and machine learning algorithms to detect and prevent face spoofing attempts. A pre-trained deep neural network model for facial recognition is employed to extract essential facial features. Subsequently, the system utilizes image manipulation detection methods to identify anomalies indicative of face spoofing attacks. The implementation showcases the simplicity and efficiency of the proposed anti-face spoofing technique, demonstrating the potential for integration into real- world applications with minimal computational overhead. The concise Python code enables easy adoption and adaptation for developers aiming to enhance the security of facial recognition systems against face spoofing threats. The experimental results demonstrate the effectiveness of the approach in accurately distinguishing between genuine and spoofed facial images, thereby contributing to the robustness of facial recognition systems in the presence of adversarial attacks. Keywords - Liveness Detection, Presentation Attack Detection, Spoof Detection Algorithms, Biometric Security, Face Recognition Robustness, 3D Face Modeling, Texture Analysis, Deep Learning Anti- Spoofing, Multi-Spectral Imaging, Behavioral Biometrics, Challenge-Response Mechanisms, Optical Flow Analysis, Pulse Detection, Surface Reflectance, Depth Sensing, Motion Analysis, Pattern Recognition, Anti-Spoofing Networks, Temporal Feature Extraction, Anomaly Detection.

An explainable MHSA enabled deep architecture with dual-scale convolutions for methane source classification using remote sensing

Methane is the second most abundant greenhouse gas after carbon dioxide. Anthropogenic sources are the dominant emitters of methane. The poor spatial resolution of satellite imagery, high interclass similarity, the multi-scalar nature of features, and the dominance of background limit the performance of the previous approaches. Further, the reliance on high-resolution imagery limits the cost-effective global application of the works introduced in the literature. To resolve this, the present work proposes a novel method for methane source classification based on open-source multi-spectral satellite imagery of Sentinel-1 and 2. The work utilizes deep dual-scale convolutions with scaled dot product self-attention calculated across the 15 composite bands of Sentinel-1 and 2 data. The incorporation of non-RGB bands along with the RGB bands further enables the model to learn the spectral differences essential for the classification. The experimental results witness the superior performance of the developed method against other considered state-of-the-art methods.

Multi-spectral light-field imager for ultra-high temperature measurement

Multi-spectral light-field imager for ultra-high temperature measurement

Pansharpening Based on Multimodal Texture Correction and Adaptive Edge Detail Fusion

Pansharpening refers to the process of fusing multispectral (MS) images with panchromatic (PAN) images to obtain high-resolution multispectral (HRMS) images. However, due to the low correlation and similarity between MS and PAN images, as well as inaccuracies in spatial information injection, HRMS images often suffer from significant spectral and spatial distortions. To address these issues, a pansharpening method based on multimodal texture correction and adaptive edge detail fusion is proposed in this paper. To obtain a texture-corrected (TC) image that is highly correlated and similar to the MS image, the target-adaptive CNN-based pansharpening (A-PNN) method is introduced. By constructing a multimodal texture correction model, intensity, gradient, and A-PNN-based deep plug-and-play correction constraints are established between the TC and source images. Additionally, an adaptive degradation filter algorithm is proposed to ensure the accuracy of these constraints. Since the TC image obtained can effectively replace the PAN image and considering that the MS image contains valuable spatial information, an adaptive edge detail fusion algorithm is also proposed. This algorithm adaptively extracts detailed information from the TC and MS images to apply edge protection. Given the limited spatial information in the MS image, its spatial information is proportionally enhanced before the adaptive fusion. The fused spatial information is then injected into the upsampled multispectral (UPMS) image to produce the final HRMS image. Extensive experimental results demonstrated that compared with other methods, the proposed algorithm achieved superior results in terms of both subjective visual effects and objective evaluation metrics.

Exploratory Analysis Using Deep Learning for Water-Body Segmentation of Peru's High-Mountain Remote Sensing Images.

High-mountain water bodies represent critical components of their ecosystems, serving as vital freshwater reservoirs, environmental regulators, and sentinels of climate change. To understand the environmental dynamics of these regions, comprehensive analyses of lakes across spatial and temporal scales are necessary. While remote sensing offers a powerful tool for lake monitoring, applications in high-mountain terrain present unique challenges. The Ancash and Cuzco regions of the Peruvian Andes exemplify these challenges. These regions harbor numerous high-mountain lakes, which are crucial for fresh water supply and environmental regulation. This paper presents an exploratory examination of remote sensing techniques for lake monitoring in the Ancash and Cuzco regions of the Peruvian Andes. The study compares three deep learning models for lake segmentation: the well-established DeepWaterMapV2 and WatNet models and the adapted WaterSegDiff model, which is based on a combination of diffusion and transformation mechanisms specifically conditioned for lake segmentation. In addition, the Normalized Difference Water Index (NDWI) with Otsu thresholding is used for comparison purposes. To capture lakes across these regions, a new dataset was created with Landsat-8 multispectral imagery (bands 2-7) from 2013 to 2023. Quantitative and qualitative analyses were performed using metrics such as Mean Intersection over Union (MIoU), Pixel Accuracy (PA), and F1 Score. The results achieved indicate equivalent performance of DeepWaterMapV2 and WatNet encoder-decoder architectures, achieving adequate lake segmentation despite the challenging geographical and atmospheric conditions inherent in high-mountain environments. In the qualitative analysis, the behavior of the WaterSegDiff model was considered promising for the proposed application. Considering that WatNet is less computationally complex, with 3.4 million parameters, this architecture becomes the most pertinent to implement. Additionally, a detailed temporal analysis of Lake Singrenacocha in the Vilcanota Mountains was conducted, pointing out the more significant behavior of the WatNet model.

Evaluating the applicability of high-density UAV LiDAR data for monitoring tundra grassland vegetation

ABSTRACT Grasslands are one of the most widespread biomes on Earth. The interaction of UAV LiDAR with grasses and herbaceous plants is an infrequently covered area of research, apart from its utilisation for the estimation of above ground biomass. To evaluate the applicability of LiDAR for monitoring grassland vegetation, two model plots in the arctic-alpine tundra (Krkonoše Mountains, Czech Republic) were selected. Throughout the growing season, UAV LiDAR point clouds (800 points/m2) and multispectral imagery (9 cm) were acquired in monthly intervals, along with reference botanical and terrestrial LiDAR data. The study provides insight into the analysis of compact low-lying vegetation at the species level. A set of experiments was conducted focusing on the analysis of LiDAR information loss, vertical strata, and structural metrics computed over the grass species/communities. Random forest was used to determine the importance of metrics by out-of-bag permutation of predictors and to classify vegetation species using UAV LiDAR-based metrics, as well as image-based digital surface models alone and in fusion with multispectral data. The vertical distribution of the UAV LiDAR points varied significantly between species and throughout the growing season. Loss at the canopy bottoms was apparent, with the lowest points corresponding to dry grass matter rather than relief. Grasslands had the highest penetration capability at the start of the growing season. In terms of metrics, maximum canopy height was the most important. The multitemporal LiDAR-derived structural metrics were able to differentiate (F-1 score above 90%) all the shrubs/trees and dominant grass Calamagrostis villosa. Mixed and low-abundance species were indistinguishable. The overall accuracy scores in a 9 (27) cm grid reached 75.1% (78.1) and 63.5% (66.4) for Bílá louka meadow and Úpské rašeliniště bog, respectively. Fusing the LiDAR-derived features with multispectral imagery did not enhance the classification results apart from the delineation of shrubs and trees.