Sentinel-2 Multispectral Data Research Articles

Exploration of grade distribution in iron mines based on rough set extreme learning machine and multispectral

Ore grade is an important indicator for evaluating the mining value of a mine. Reasonable mining based on ore grade distribution can aid in sustainable development and grade control within mining areas. Therefore, this paper aims to utilize Sentinel-2 multispectral data and an extreme learning machine (ELM) to rapidly explore the grade distribution in iron ore mines. First, direct orthogonal signal correction and mathematical transforms are used to correct and enhance multispectral information. Then, we propose a rough set ELM (RS-ELM) to learn multispectral data for grade distribution exploration. Specifically, we first discretize the hidden layer matrix (H) of the ELM and calculate the dependency degrees of the nodes on each other according to the rough set method. Then, the nodes with high dependency degree are deleted to ensure the lightness of the network structure and reduce the complexity of the ELM. Furthermore, a whitening transformation is performed on H to improve numerical stability. Comparison experiments prove the effectiveness of the RS-ELM. Finally, the mine grade distribution exploration model is established by using Sentinel-2 multispectral data and RS-ELM, and the grade distribution map of the mine is drawn. The distribution map clearly shows the trend of grade distribution in the mine. Moreover, based on the cut-off and industrial grades, we categorize the mine area into three zones: non-ore, secondary ore, and main ore areas. This categorization provides a foundation for developing the mine’s mining plan and grade control.

Assessing the Effect of Water on Submerged and Floating Plastic Detection Using Remote Sensing and K-Means Clustering

Marine and freshwater plastic pollution is a worldwide problem affecting ecosystems and human health. Although remote sensing has been used to map large floating plastic rafts, there are research gaps in detecting submerged plastic due to the limited amount of in situ data. This study is the first to collect in situ data on submerged and floating plastics in a freshwater environment and analyse the effect of water submersion on the strength of the plastic signal. A large 10 × 10 m artificial polymer tarpaulin was deployed in a freshwater lake for a two-week period and was captured by a multi-sensor and multi-resolution unmanned aerial vehicle (UAV) and satellite. Spectral analysis was conducted to assess the attenuation of individual wavelengths of the submerged tarpaulin in UAV hyperspectral and Sentinel-2 multispectral data. A K-Means unsupervised clustering algorithm was used to classify the images into two clusters: plastic and water. Additionally, we estimated the optimal number of clusters present in the hyperspectral dataset and found that classifying the image into four classes (water, submerged plastic, near surface plastic and buoys) significantly improved the accuracy of the K-Means predictions. The submerged plastic tarpaulin was detectable to ~0.5 m below the water surface in near infrared (NIR) (~810 nm) and red edge (~730 nm) wavelengths. However, the red spectrum (~669 nm) performed the best with ~84% true plastic positives, classifying plastic pixels correctly even to ~1 m depth. These individual bands outperformed the dedicated Plastic Index (PI) derived from the UAV dataset. Additionally, this study showed that in neither Sentinel-2 bands, nor the derived indices (PI or Floating Debris Index (FDI), it is currently possible to determine if and how much of the tarpaulin was under the water surface, using a plastic tarpaulin object of 10 × 10 m. Overall, this paper showed that spatial resolution was more important than spectral resolution in detecting submerged tarpaulin. These findings directly contributed to Sustainable Development Goal 14.1 on mapping large marine plastic patches of 10 × 10 m and could be used to better define systems for monitoring submerged and floating plastic pollution.

Multisource remote sensing monitoring and analyzing for land subsidence and crop growth in a coal mining area under different rainfall conditions

Coal has been crucial in driving economic development and production construction. However, the mining-induced subsidence may cause irreversible damage to the surrounding environment of vegetation growth. Meanwhile, with the worsening of global warming, the frequency and intensity of extreme water-related weather events, such as droughts and excessive rainfall, are on the rise, which leads to heightened impacts on ecosystems and agricultural production. Consequently, extreme water-related weather, the distribution of land subsidence, and its effect on vegetation have attracted significant attention. Based on the Sentinel-1 radar data and Sentinel-2 multispectral data from 2017 to 2022, the SBAS-InSAR technology, the object-oriented classification, and the Normalized Difference Vegetation Index (NDVI) were employed respectively in the study to obtain the spatial-temporal evolution of land subsidence, subsidence-induced water, and crop growth in Tiefa mining area, a representative coal mining area in Northeast China. Moreover, the relationship between land subsidence, subsidence-induced water, and vegetation change was analyzed combined with summer precipitation data. The results showed that: (1) The average cumulative subsidence of the mining area was 256.8 mm, and the subsidence area was 42.525 km2 for the six years. Among them, the heaviest subsidence reached a maximum of 380.5 mm in 2022, and the largest subsidence area was 20.109 km2 in 2017. (2) When the rainfall was excessive, the area of subsidence-induced water would increase sharply, with a proportion jumping to 9.71% from 5.37%, which indicated the subsidence would further amplify the destructive effect of excessive rainfall and waterlogging on land resources. (3) In addition to the existing water pits, ground cracks and shallow subsidence pits appeared under the influence of underground coal mining. The direct impact of ground cracks on crops was not apparent, while the effect of subsidence pits on crops under different rainfall conditions was dual character. In dry years, crops in the subsidence pits could grow better due to higher soil moisture. In wet years, crops in the subsidence pits would suffer the more severe waterlogging. The research results are of great significance for further understanding the influence of coal mining on surface vegetation in mining areas in Northeast China.

Improving PRISMA hyperspectral spatial resolution and geolocation by using Sentinel-2: development and test of an operational procedure in urban and rural areas

Hyperspectral (HS) satellites like PRISMA (PRecursore IperSpettrale della Missione Applicativa) offer remarkable capabilities, yet they are constrained by a relatively coarse spatial resolution, curbing their efficacy in those applications that require pinpoint accuracy. Here we propose a fusion process, aimed at the enhancement of PRISMA HS spatial resolution by using the spatial and spectral information of Sentinel-2 multispectral (MS) data (HS-MS fusion process), validated against four airborne HS flights simultaneous to satellite overpasses on different land use distributions. Adopting the PRISMA panchromatic (PAN) image, the proposed solution was also compared with the results of a HS-PAN pansharpening process. A two-steps operational workflow is proposed, based on two state-of-the-art and open-source algorithms. The first step consisted of the geocoding of PRISMA L2 products using Senintel-2 as reference and was accomplished with the phase-based algorithm implemented in AROSICS (Automated and Robust Open-Source Image Co-registration Software). The geometric displacement in L2 data was found to be between 80 m and 250 m, irregularly spatially distributed throughout the same scene and among scenes, and it was corrected by means of thousands of regularly spatially distributed tie points. A second-order polynomial transformation function was integrated in the algorithm. The second step consisted of employing the HySure (HS Super resolution) fusion algorithm to perform both the HS-MS fusion and the HS-PAN pansharpening, returning a PRISMA HS improved dataset with a spatial resolution of 10 m and 5 m, respectively. Four different per-band accuracy metrics were used to evaluate the accuracy of both products against airborne data. Overall, HS-MS data achieved increased accuracy in all validation metrics, i.e. + 28 % (root mean square error, RMSE), +23 % (spectral angle mapper, SAM), +7% (peak signal-to-noise ratio, PSNR) and + 11 % (universal image quality index, UIQI), with respect of HS-PAN data. These outcomes showed that using the spectral information of Sentinel-2 both spectral and spatial patterns were reconstructed more consistently in three different urban and rural scenarios, avoiding the presence of blur and at-edge artefacts as opposed to HS-PAN pansharpening, therefore suggesting an optimal strategy for satellite HS data resolution enhancement.

A dataset of spatial distribution of tea plantations at 10 m resolution in Fujian Province from 2000 to 2020

Being a major tea producing province in China, Fujian Province is badly in need of quick and accurate spatial distribution of tea plantation for decision-making in both the agricultural economic development and the ecological environment construction for the province. This study retrieved and processed Sentinel-1 (S1) radar data and Sentinel-2 (S2) multispectral data on the GEE cloud platform; and it extracted 98 features, such as spectral features, texture features, and terrain features from the terrain data. The recursive elimination support vector machine algorithm (SVM RFE) is used to screen the characteristic variables, resulting in the creation of 4 feature combination schemes. Using a support vector machine (SVM) classifier to extract the distribution data of tea plantations and assessing the accuracy of the 4 feature combination schemes, we obtained the spatial distribution data of tea plantations at 10 m resolution in Fujian Province in 2020. On this basis, we used the GEE cloud platform to access the vegetation disturbance information in Fujian Province from 2000 to 2020. We finally obtained a dataset of spatial distribution of tea plantations at 10 m resolution in Fujian Province from 2000 to 2020 by excluding the non-tea plantation areas from the images between 2000 and 2015 with the mask generated from the 2020 tea garden extraction results. This dataset has been manually validated using sample points from key tea-producing counties and townships. The results indicate an extraction accuracy of over 92% for tea plantations in 2020. The extraction accuracy of tea plantations obtained using interference data removal method in 2000, 2005, 2010, and 2015 was all above 80%. The dataset with a high accuracy in tea plantation extraction can provide support for relevant departments in tea plantation management.

Leveraging Sentinel-2 and Geographical Information Systems in Mapping Flooded Regions around the Sesia River, Piedmont, Italy

Sentinel-2 data are crucial in mapping flooded areas as they provide high spatial and spectral resolution but under cloud-free weather conditions. In the present study, we aimed to devise a method for mapping a flooded area using multispectral Sentinel-2 data from optical sensors and Geographical Information Systems (GISs). As a case study, we selected a site located in Northern Italy that was heavily affected by flooding events on 3 October 2020, when the Sesia River in the Piedmont region was hit by severe weather disturbance, heavy rainfall, and strong winds. The method developed for mapping the flooded area was a thresholding technique through spectral water indices. More specifically, the Normalized Difference Water Index (NDWI) and the Modified Normalized Difference Water Index (MNDWI) were chosen as they are among the most widely used methods with applications across various environments, including urban, agricultural, and natural landscapes. The corresponding flooded area product from the Copernicus Emergency Management Service (EMS) was used to evaluate the flooded area predicted by our method. The results showed that both indices captured the flooded area with a satisfactory level of detail. The NDWI demonstrated a slightly higher accuracy, where it also appeared to be more sensitive to the separation of water from soil and areas with vegetation cover. The study findings may be useful in disaster management linked to flooded-area mapping and area rehabilitation mapping following a flood event, and they can also valuably assist decision and policy making towards a more sustainable environment.

Improved Classification of Coastal Wetlands in Yellow River Delta of China Using ResNet Combined with Feature-Preferred Bands Based on Attention Mechanism

The Yellow River Delta wetlands in China belong to the coastal wetland ecosystem, which is one of the youngest and most characteristic wetlands in the world. The Yellow River Delta wetlands are constantly changed by inland sediment and the influence of waves and storm surges, so the accurate classification of the coastal wetlands in the Yellow River Delta is of great significance for the rational utilization, development and protection of wetland resources. In this study, the Yellow River Delta sentinel-2 multispectral data were processed by super-resolution synthesis, and the feature bands were optimized. The optimal feature-band combination scheme was screened using the OIF algorithm. A deep learning model attention mechanism ResNet based on feature optimization with attention mechanism integration into the ResNet network is proposed. Compared with the classical machine learning model, the AM_ResNet model can effectively improve the classification accuracy of the wetlands in the Yellow River Delta. The overall accuracy was 94.61% with a Kappa of 0.93, and they were improved by about 6.99% and 0.1, respectively, compared with the best-performing Random Forest Classification in machine learning. The results show that the method can effectively improve the classification accuracy of the wetlands in the Yellow River Delta.

Remote Quantification of Soil Organic Carbon: Role of Topography in the Intra-Field Distribution

Soil organic carbon (SOC) measurements are an indicator of soil health and an important parameter for the study of land-atmosphere carbon fluxes. Field sampling provides precise measurements at the sample location but entails high costs and cannot provide detailed maps unless the sampling density is very high. Remote sensing offers the possibility to quantify SOC over large areas in a cost-effective way. As a result, numerous studies have sought to quantify SOC using Earth observation data with a focus on inter-field or regional distributions. This study took a different angle and aimed to map the spatial distribution of SOC at the intra-field scale, since this distribution provides important insights into the biophysiochemical processes involved in the retention of SOC. Instead of solely using spectral measurements to quantify SOC, topographic and spectral features act as predictor variables. The necessary data on study fields in South-East England was acquired through a detailed SOC sampling campaign, including a LiDAR survey flight. Multi-spectral Sentinel-2 data of the study fields were acquired for the exact day of the sampling campaign, and for an interval of 18 months before and after this date. Random Forest (RF) and Support Vector Regression (SVR) models were trained and tested on the spectral and topographical data of the fields to predict the observed SOC values. Five different sets of model predictors were assessed, by using independently and in combination, single and multidate spectral data, and topographical features for the SOC sampling points. Both, RF and SVR models performed best when trained on multi-temporal Sentinel-2 data together with topographic features, achieving validation root-mean-square errors (RMSEs) of 0.29% and 0.23% SOC, respectively. These RMSEs are competitive when compared with those found in the literature for similar models. The topographic wetness index (TWI) exhibited the highest permutation importance for virtually all models. Given that farming practices within each field are the same, this result suggests an important role of soil moisture in SOC retention. Contrary to findings in dryer climates or in studies encompassing larger areas, TWI was negatively related to SOC levels in the study fields, suggesting a different role of soil wetness in the SOC storage in climates characterized by excess rainfall and poorly drained soils.

Exploring optimal integration schemes for Sentinel-1 SAR and Sentinel-2 multispectral data in land cover mapping across different atmospheric conditions

Integrating remote sensing data, such as Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 multispectral data, can provide valuable insights for this task. However, in tropical regions, such as Yogyakarta, Indonesia, atmospheric interference from cloud cover and haze can result in spectral confusion and decreased usability of multispectral data, leading to reduced classifier accuracy. This study investigates the impact of integrating Sentinel-1 SAR and Sentinel-2 multispectral data and their derivatives on land cover mapping in part of Yogyakarta under hazy and clear atmospheric conditions. This study employed four Schemes: (1) using only SAR data and its derivatives, (2) using only multispectral data and its derivatives, (3) combining SAR, multispectral, and their derivatives, and (4) combining SAR, multispectral, and their derivatives with feature selection using Recursive Feature Elimination. The XGBoost classification algorithm tuned using Bayesian optimization was used for classification, and the accuracy and efficiency (processing time) of each Scheme were evaluated. The results showed that integrating SAR data and optical data with clear and hazy condition increased the accuracy by 4 % (clear) to 14.58 % (hazy). The integration of SAR and optical data had the highest accuracy (79.58% on hazy imagery and 84.58% on clear imagery) but longer processing time. However, the feature selection conducted in decreased model complexity and processing time, with a reduction in processing time of 78.74% on hazy imagery and 49.89% as compared to utilizing the full SAR and optical data variables. Lastly, the McNemar test concluded the significance of integrating SAR data for mapping land cover, especially with hazy optical data.

High-spatial-resolution surface soil moisture retrieval using the Deep Forest model in the cloud environment over the Tibetan Plateau

ABSTRACT As a key climate variable, soil moisture plays a crucial role in drought detection, flood warning, and crop yield prediction. In recent years, the demand for high-spatial-resolution soil moisture has increased, particularly in environmental management. In this study, Copernicus Sentinel-1 synthetic aperture radar data, Sentinel-2 multi-spectral data, and other auxiliary data (land cover types, soil texture, etc.) were used to retrieve surface soil moisture (10 m) in the cloud environment (Google Earth Engine + Google Colab + Google Drive) over the Tibetan Plateau, and an entirely data-driven machine learning-based model called Deep Forest was adopted. We discussed the application of the Deep Forest model and compared it with other machine learning models. Overall, on the basis of 10-fold cross-validation, the modified Deep Forest model performed the best, with estimate accuracy of 0.834 and 0.038 m3·m−3 in terms of coefficient of determination ( R 2 ) and unbiased Root Mean Square Error (ubRMSE), respectively. It also demonstrated the best performance in site-based validation ( R 2 of 0.606 and ubRMSE of 0.092 m3·m−3). In addition, the framework for the data acquisition, data preprocessing, model training, and soil moisture mapping in this study was completed in the cloud environment, which facilitated the entire retrieval process. This work provides new ideas beyond the retrieval model for other related studies.

Monitoring Forest Diversity under Moso Bamboo Invasion: A Random Forest Approach

Moso bamboo (Phyllostachys edulis) is a crucial species among the 500 varieties of bamboo found in China and plays an important role in providing ecosystem services. However, remote sensing studies on the invasion of Moso bamboo, especially its impact on forest biodiversity, are limited. Therefore, we explored the feasibility of using Sentinel-2 multispectral data and digital elevation data from the Shuttle Radar Topography Mission and random forest (RF) algorithms to monitor changes in forest diversity due to the spread of Moso bamboo. From October to November 2019, researchers conducted field surveys on 100 subtropical forest plots in Zhejiang Province, China. Four biodiversity indices (Margalef, Shannon, Simpson, and Pielou) were calculated from the survey data. Subsequently, after completing 100 epochs of training and testing, we developed the RF prediction model and assessed its performance using three key metrics: coefficient of determination, root mean squared error, and mean absolute error. Our results showed that the RF model has a strong predictive ability for all indices except for the Pilou index, which has an average predictive ability. These results demonstrate the feasibility of using remote sensing to monitor forest diversity changes caused by the spreading of Moso bamboo.

Estimation of the Biogeochemical and Physical Properties of Lakes Based on Remote Sensing and Artificial Intelligence Applications

Lakes play a crucial role in the global biogeochemical cycles through the transport, storage, and transformation of different biogeochemical compounds. Their regulatory service appears to be disproportionately important relative to their small areal extent, necessitating continuous monitoring. This study leverages the potential of optical remote sensing sensors, specifically Sentinel-2 Multispectral Imagery (MSI), to monitor and predict water quality parameters in lakes. Optically active parameters, such as chlorophyll a (CHL), total suspended matter (TSM), and colored dissolved matter (CDOM), can be directly detected using optical remote sensing sensors. However, the challenge lies in detecting non-optically active substances, which lack direct spectral characteristics. The capabilities of artificial intelligence applications can be used in the identification of optically non-active compounds from remote sensing data. This study aims to employ a machine learning approach (combining the Genetic Algorithm (GA) and Extreme Gradient Boost (XGBoost)) and in situ and Sentinel-2 Multispectral Imagery data to construct inversion models for 16 physical and biogeochemical water quality parameters including CHL, CDOM, TSM, total nitrogen (TN), total phosphorus (TP), phosphate (PO4), sulphate, ammonium nitrogen, 5-day biochemical oxygen demand (BOD5), chemical oxygen demand (COD), and the biomasses of phytoplankton and cyanobacteria, pH, dissolved oxygen (O2), water temperature (WT) and transparency (SD). GA_XGBoost exhibited strong predictive capabilities and it was able to accurately predict 10 biogeochemical and 2 physical water quality parameters. Additionally, this study provides a practical demonstration of the developed inversion models, illustrating their applicability in estimating various water quality parameters simultaneously across multiple lakes on five different dates. The study highlights the need for ongoing research and refinement of machine learning methodologies in environmental monitoring, particularly in remote sensing applications for water quality assessment. Results emphasize the need for broader temporal scopes, longer-term datasets, and enhanced model selection strategies to improve the robustness and generalizability of these models. In general, the outcomes of this study provide the basis for a better understanding of the role of lakes in the biogeochemical cycle and will allow the formulation of reliable recommendations for various applications used in the studies of ecology, water quality, the climate, and the carbon cycle.

Forest Gap Extraction Based on Convolutional Neural Networks and Sentinel-2 Images

As a type of small-scale disturbance, forest gap and its accurate extraction are of great significance to monitor forest long-term dynamics, to choose forest recovery mode and to predict forest recovery pace. Currently, airborne LiDAR and high-resolution multi-spectral data are commonly used to accurately classify forest gaps, but they are costly to acquire and have limited time and space availability. In contrast, the Sentinel-2 multi-spectral data with a 10 m spatial resolution overcomes these drawbacks in forest gap extraction. In this work, an integrated framework that combines multi-source remote sensing, machine learning and deep learning to extract forest gap in wide regions was proposed and tested in three sites. First, LiDAR, Sentinel series and random forest (RF) algorithm were synergized to produce a canopy height product in model training site. On this basis, samples for forest canopy, forest gap and non-such were identified from LiDAR-derived canopy height model (CHM) and Sentinel-based canopy height inversion (HI) data to train forest gap extraction models by applying the Deep Forest (DF) and Convolutional Neural Networks (CNN) algorithms, followed by a comparison of the accuracy and the transferability among the four models (DF-CHM, DF-HI, CNN-CHM and CNN-HI). The results indicated that the R2 and RMSE of Sentinel-based canopy height retrievals were estimated at 0.63, and 7.85 m respectively, the difference in the mean height and standard deviation between HI and CHM was 0.03 m and 4.7 m respectively. And there was a spatial agreement of about 98.60% between the HI-identified samples and the CHM-identified samples, with an agreement of 54.89% for the forest gap class. The CNN-HI model had the highest accuracy in both transfer learning test sites, with an overall accuracy (OA) of 0.85 and 0.87, Kappa coefficient at 0.78 and 0.81, respectively, proving that it has good transferability. Conversely, the DF-based models generally gave poorer accuracy and transferability. This study demonstrates that combining Sentinel-2 multi-spectral data and CNN algorithm is feasible and effective in forest gap extraction applications over wide regions.

Insights into post-emplacement lava flow dynamics at Mt. Etna volcano from 2016 to 2021 by synthetic aperture radar and multispectral satellite data

Insights into post-emplacement lava flow dynamics at Mt. Etna volcano from 2016 to 2021 by synthetic aperture radar and multispectral satellite data

Caution is needed across Mediterranean ecosystems when interpreting wall-to-wall fire severity estimates based on spectral indices

The use of comprehensive, multi-strata fire severity metrics measured in the field, such as the composite burn index (CBI), is the most commonly used approach to calibrate remote sensing-based products and obtain wall-to-wall fire severity estimates. However, the extent to which specific ecological changes as measured by individual CBI attributes per stratum actually drive the spectral variability in Mediterranean fire-prone ecosystems has not been deciphered yet. In addition, it is not clear if these relationships are consistent across different Mediterranean ecosystems, particularly when fire effects across strata can be decoupled. To bridge these knowledge gaps, we examined the fire severity divergence among CBI strata in different types of Mediterranean forest (both conifer- and broadleaf-dominated) and shrubland ecosystems with 240 plots distributed across five wildfires in the westernmost part of the Mediterranean Basin and Chile. Then, we compared the relationship of two spectral fire severity indices with the CBI scores by strata. Finally, we used a wrapper algorithm (VSURF) around Random Forest regression to assess the potential contribution and redundancy of individual CBI attributes in shaping the spectral response of fire severity indices computed from multispectral Sentinel-2 data. The Relativized Burn Ratio (RBR) index fitted CBI field data better than the differenced Normalized Burn Ratio (dNBR). Fire effects were strongly decoupled and, for example, the substrate stratum experienced the lowest severity in conifer forests and shrublands, whereas the upper strata remained largely unaffected in broadleaf forests. This has substantial implications since we found differential responses of the RBR signal to fire effects by strata as measured by distinct individual CBI attributes. Specifically, the fire impact on the green vegetation fraction of upper strata in broadleaf and conifer forests, and on the substrate stratum in shrublands, were identified as non-redundant and most contributing fire effects shaping the spectral signal variability in burned Mediterranean ecosystems. These results, together with decoupled fire severity effects across strata, suggest that aggregated CBI metrics may obscure ecologically relevant fire-induced changes, and noticeable disconnects may exist between wall-to-wall fire severity estimates and actual fire effects in the field.

Combining multi-temporal airborne LiDAR and Sentinel-2 multispectral data for assessment of disturbances and recovery of mangrove forests

Disturbances such as tropical cyclones and insect pests in mangroves can cause defoliation, tree mortality, and other changes in ecosystem processes. Understanding the resistance and resilience of mangroves to disturbance is critical to developing strategies for conservation. However, most studies apply multi-temporal optical data which have limited power to detect structural changes, especially for forests with complex architectures. We combined multispectral Sentinel-2 (S2) images and airborne LiDAR Scanning (ALS) datasets to assemble a comprehensive view of the effects of two disturbance events (a moth pest and a super-typhoon) on mangroves in Mai Po, Hong Kong. A series of normalized difference vegetation index (NDVI) estimates derived from S2 data indicated changes in greenness before and after the moth pest and typhoon events. An object-based stratification method was applied with ALS data to separate the overstory and understory to distinguish stratum changes. The results showed that moth larvae were more likely to encroach leafy mangroves of Avicennia marina. Double-layered and single-layered short mangroves have better resistance to typhoons than younger tall mangroves without understory beneath. NDVI recovered rapidly after three to six months post-disturbance but significant changes in canopy structures were found from the ALS data. Canopy gaps increased both in size and quantity in mature overstory areas, likely benefitting the growth of the understories beneath. Finally, the understory area grew resulting in a transition from single-layered to double-layered structures. The combination of multi-temporal LiDAR and multispectral data used here highlights the power of complementary remote sensing products in documenting mangrove ecosystem processes.

S2MetNet: A novel dataset and deep learning benchmark for methane point source quantification using Sentinel-2 satellite imagery

Methane, as a crucial greenhouse gas, plays a significant role in global warming, contributing to approximately one-quarter of the observed climate change since pre-industrial times. Consequently, the detection and quantification of major methane emitters are vital in addressing this issue effectively. Satellite sensors with shortwave infrared (SWIR) spectral bands provide valuable information for monitoring methane emissions. For example, Sentinel-2 multispectral data have the capability to detect methane plumes of large point sources. As such, a wide range of quantification approaches have been developed to quantify methane source rates based on this dataset. Most of the existing methods, however, require auxiliary data, such as wind speed, and have large uncertainties. In this study, we introduce a novel approach based on deep learning models to enhance the precision of methane quantification using Sentinel-2 data without the reliance on external data sources. To train the proposed deep learning model, a comprehensive benchmark dataset has been generated, using Sentinel-2 data. This dataset is created by integrating simulated plumes and background noise extracted from real Sentinel-2 images. This approach ensures the integration of realistic environmental conditions within the simulated data, enhancing the robustness and reliability of our proposed model. The generated benchmark dataset is utilized in different deep learning architectures, namely VGG-19, ResNet-50, Inception-v3, DenseNet-121, Swin-T, and EfficientNet-V2L, to estimate methane source rate. The performance of deep models has been evaluated in three learning strategies, namely from scratch, transfer-learning, and fine-tuning. The fine-tuned EfficientNet-V2L achieves the highest accuracy with root-mean-square error (RMSE), mean absolute percentage error (MAPE), and Pearson R of 2101 kg h−1, 10.05%, and 95.70%, respectively. More importantly, the proposed model demonstrates superior performance compared to conventional physical-based quantification methods (e.g., integrated mass enhancement) and recently developed deep learning model techniques (e.g., MethaNet). In particular, the proposed model exhibits an improvement of approximately 1287 kg h−1 in terms of RMSE, a 3.92% reduction in MAPE, and a 5.01% enhancement in R compared to the IME method. These results highlight the advancements achieved by the proposed approach in accurately quantifying methane emissions using Sentinel-2 imagery. The generated benchmark dataset and the developed deep learning model presented in this study serve as a fundamental resource and constructive framework for future research, promoting extensive implementation across various methane monitoring scenarios on different satellites and in distinct geographic regions, which delivering greater effectiveness to global methane emission monitoring initiatives.

Lake Cyanobacterial Bloom Color Recognition and Spatiotemporal Monitoring with Google Earth Engine and the Forel-Ule Index

Cyanobacterial blooms represent a significant environmental problem, threatening aquatic ecosystems worldwide. Caused by the eutrophication of water bodies and global climate change, these blooms have altered freshwater ecosystems worldwide during recent decades. Although cyanobacterial blooms are typically caused by blue-green cyanobacteria, which derive their color from the phycocyanin pigment, other pigmented cyanobacterial blooms have been frequently observed in water bodies. These blooms pose a serious environmental threat to inland waters, endangering global public health and aquatic ecosystems. Therefore, comprehending the mechanism of color variation in cyanobacterial blooms is crucial for revealing the outbreak mechanism and implementing effective prevention and control measures. This study developed a human–machine interactive workflow for extracting cyanobacterial blooms and recognizing their colors based on the Forel-Ule index and Sentinel-2 MultiSpectral Instrument data. Using this workflow, the authors conducted spatiotemporal analysis and statistical analysis of bloom color for cyanobacterial blooms in four typical eutrophic lakes from 2019 to 2022. The findings indicated a declining trend in cyanobacterial blooms across the four studied lakes over the years, among which Hulun Lake experienced an annual increase in cyanobacterial blooms and emerged as the lake with the most severe outbreak of such blooms in 2022. The yellowing status of cyanobacterial blooms varied among the four lakes, with Taihu Lake and Dianchi Lake exhibiting a relatively high proportion of green-yellow and yellow cyanobacterial blooms, followed by Chaohu Lake, whereas Hulun Lake had the lowest occurrence. The workflow developed in this study was implemented in Google Earth Engine and provided an automated, integrated, and rapid monitoring solution for the long-term monitoring and color recognition of cyanobacterial blooms.

Automated glacier extraction using a Transformer based deep learning approach from multi-sensor remote sensing imagery

Glaciers serve as sensitive indicators of climate change, making accurate glacier boundary delineation crucial for understanding their response to environmental and local factors. However, traditional semi-automatic remote sensing methods for glacier extraction lack precision and fail to fully leverage multi-source data. In this study, we propose a Transformer-based deep learning approach to address these limitations. Our method employs a U-Net architecture with a Local-Global Transformer (LGT) encoder and multiple Local-Global CNN Blocks (LGCB) in the decoder. The model design aims to integrate both global and local information. Training data for the model were generated using Sentinel-1 Synthetic Aperture Radar (SAR) data, Sentinel-2 multispectral data, High Mountain Asia (HMA) Digital Elevation Model (DEM), and Shuttle Radar Topography Mission(SRTM) DEM. The ground truth was obtained for a glaciated area of 1498.06 km2 in the Qilian mountains using classic band ratio and manual delineation based on 2 m resolution GaoFen (GF) imagery. A series of experiments including the comparison between different models, model modules and data combinations were conducted to evaluate the model accuracy. The best overall accuracy achieved was 0.972. Additionally, our findings highlight the significant contribution of Sentinel-2 data to glacier extraction.

Sentinel-2 Time Series and Classifier Fusion to Map an Aquatic Invasive Plant Species along a River—The Case of Water-Hyacinth

Freshwater ecosystems host high levels of biodiversity but are also highly vulnerable to biological invasions. Aquatic Invasive Alien Plant Species (aIAPS) can cause detrimental effects on freshwater ecosystems and their services to society, raising challenges to decision-makers regarding their correct management. Spatially and temporally explicit information on the occurrence of aIAPS in dynamic freshwater systems is essential to implement efficient regional and local action plans. The use of unmanned aerial vehicle imagery synchronized with free Sentinel-2 multispectral data allied with classifier fusion techniques may support more efficient monitoring actions for non-stationary aIAPS. Here, we explore the advantages of such a novel approach for mapping the invasive water-hyacinth (Eichhornia crassipes) in the Cávado River (northern Portugal). Invaded and non-invaded areas were used to explore the evolution of spectral attributes of Eichhornia crassipes through a time series (processed by a super-resolution algorithm) that covers March 2021 to February 2022 and to build an occurrence dataset (presence or absence). Analysis of the spectral behavior throughout the year allowed the detection of spectral regions with greater capacity to distinguish the target plant from the surrounding environment. Classifier fusion techniques were implemented in the biomod2 predictive modelling package and fed with selected spectral regions to firstly extract a spectral signature from the synchronized day and secondly to identify pixels with similar reflectance values over time. Predictions from statistical and machine-learning algorithms were ensembled to map invaded spaces across the whole study area during all seasons with classifications attaining high accuracy values (True Skill Statistic, TSS: 0.932; Area Under the Receiver Operating Curve, ROC: 0.992; Kappa: 0.826). Our results provide evidence of the potential of our approach to mapping plant invaders in dynamic freshwater systems over time, applicable in the assessment of the success of control actions as well as in the implementation of long-term strategic monitoring.