Search Results (224)

The salinization of agricultural soils is a serious threat to farming and ecological balance in arid and semi-arid regions. Accurate estimation of soil water-soluble ions (calcium, carbonate, magnesium, and sulfate) is necessary for correct monitoring of soil salinization and sustainable land management. Hyperspectral ground-based data are valuable in soil salinization monitoring, but the acquisition cost is high, and the coverage is small. Therefore, this study proposes a two-stage deep learning framework with multispectral remote-sensing images. First, the wavelet transform is used to enhance the Transformer and extract fine-grained spectral features to reconstruct the ground-based hyperspectral data. A comparison of ground-based hyperspectral data shows that the reconstructed spectra match the measured data in the 450–998 nm range, with R² up to 0.98 and MSE = 0.31. This high similarity compensates for the low spectral resolution and weak feature expression of multispectral remote-sensing data. Subsequently, this enhanced spectral information was integrated and fed into a novel multiscale self-attentive Transformer model (MSATransformer) to invert four water-soluble ions. Compared with BPANN, MLP, and the standard Transformer model, our model remains robust across different spectra, achieving an R² of up to 0.95 and reducing the average relative error by more than 30%. Among them, for the strongly responsive ions magnesium and sulfate, R² reaches 0.92 and 0.95 (with RMSE of 0.13 and 0.29 g/kg, respectively). For the weakly responsive ions calcium and carbonate, R² stays above 0.80 (RMSE is below 0.40 g/kg). The MSATransformer framework provides a low-cost and high-accuracy solution to monitor soil salinization at large scales and supports precision farmland management. Full article

While deep learning has advanced object detection through hierarchical feature learning and end-to-end optimization, conventional random sampling paradigms exhibit critical limitations in addressing hyperspectral ambiguity and low-distinguishability challenges in ground-based cloud detection. To overcome these limitations, we propose CurriCloud, a loss-adaptive curriculum framework featuring three key innovations: (1) real-time sample evaluation via Unified Batch Loss (UBL) for difficulty measurement, (2) stabilized training monitoring through a sliding window queue mechanism, and (3) progressive sample selection aligned with model capability using meteorology-guided phase-wise threshold scheduling. Extensive experiments on the ALPACLOUD benchmark demonstrate CurriCloud’s effectiveness across diverse architectures (YOLOv10s, SSD, and RT-DETR-R50), achieving consistent improvements of +3.1% to +11.4% mAP50 over both random sampling baselines and existing curriculum learning methods. Full article

Background/Objectives: This research presents a novel analytical method for breast tumor characterization and tissue classification by leveraging intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) combined with hyperspectral imaging techniques and deep learning. Traditionally, dynamic contrast-enhanced MRI (DCE-MRI) is employed for breast tumor diagnosis, but it involves gadolinium-based contrast agents, which carry potential health risks. IVIM imaging extends conventional diffusion-weighted imaging (DWI) by explicitly separating the signal decay into components representing true molecular diffusion ($D$) and microcirculation of capillary blood (pseudo-diffusion or $D*$). This separation allows for a more comprehensive, non-invasive assessment of tissue characteristics without the need for contrast agents, thereby offering a safer alternative for breast cancer diagnosis. The primary purpose of this study was to evaluate different methods for breast tumor characterization using IVIM-DWI data treated as hyperspectral image stacks. Dice similarity coefficients and Jaccard indices were specifically used to evaluate the spatial segmentation accuracy of tumor boundaries, confirmed by experienced physicians on dynamic contrast-enhanced MRI (DCE-MRI), emphasizing detailed tumor characterization rather than binary diagnosis of cancer. Methods: The data source for this study consisted of breast MRI scans obtained from 22 patients diagnosed with mass-type breast cancer, resulting in 22 distinct mass tumor cases analyzed. MR images were acquired using a 3T MRI system (Discovery MR750 3.0 Tesla, GE Healthcare, Chicago, IL, USA) with axial IVIM sequences and a bipolar pulsed gradient spin echo sequence. Multiple b-values ranging from 0 to 2500 s/mm² were utilized, specifically thirteen original b-values (0, 15, 30, 45, 60, 100, 200, 400, 600, 1000, 1500, 2000, and 2500 s/mm²), with the last four b-value images replicated once for a total of 17 bands used in the analysis. The methodology involved several steps: acquisition of multi-b-value IVIM-DWI images, image pre-processing, including correction for motion and intensity inhomogeneity, treating the multi-b-value data as hyperspectral image stacks, applying hyperspectral techniques like band expansion, and evaluating three tumor detection methods: kernel-based constrained energy minimization (KCEM), iterative KCEM (I-KCEM), and deep neural networks (DNNs). The comparisons were assessed by evaluating the similarity of the detection results from each method to ground truth tumor areas, which were manually drawn on DCE-MRI images and confirmed by experienced physicians. Similarity was quantitatively measured using the Dice similarity coefficient and the Jaccard index. Additionally, the performance of the detectors was evaluated using 3D-ROC analysis and its derived criteria (AUC_OD, AUC_TD, AUC_BS, AUC_TD−BS, AUC_ODP, AUC_SNPR). Results: The findings objectively demonstrated that the DNN method achieved superior performance in breast tumor detection compared to KCEM and I-KCEM. Specifically, the DNN yielded a Dice similarity coefficient of 86.56% and a Jaccard index of 76.30%, whereas KCEM achieved 78.49% (Dice) and 64.60% (Jaccard), and I-KCEM achieved 78.55% (Dice) and 61.37% (Jaccard). Evaluation using 3D-ROC analysis also indicated that the DNN was the best detector based on metrics like target detection rate and overall effectiveness. The DNN model further exhibited the capability to identify tumor heterogeneity, differentiating high- and low-cellularity regions. Quantitative parameters, including apparent diffusion coefficient ($ADC$), pure diffusion coefficient ($D$), pseudo-diffusion coefficient ($D*$), and perfusion fraction ($PF$), were calculated and analyzed, providing insights into the diffusion characteristics of different breast tissues. Analysis of signal intensity decay curves generated from these parameters further illustrated distinct diffusion patterns and confirmed that high cellularity tumor regions showed greater water molecule confinement compared to low cellularity regions. Conclusions: This study highlights the potential of combining IVIM-DWI, hyperspectral imaging techniques, and deep learning as a robust, safe, and effective non-invasive diagnostic tool for breast cancer, offering a valuable alternative to contrast-enhanced methods by providing detailed information about tissue microstructure and heterogeneity without the need for contrast agents. Full article

Estimating wheat traits based on spectral reflectance measurements and machine learning remains challenging due to the large datasets required for model training and testing. To overcome this limitation, a simulated dataset was generated using the radiative transfer model (RTM) PROSAIL and inverted based on an artificial neural network (ANN). Field experiments were conducted in Eastern Austria to measure spectral reflectance and destructively sample plants to measure the wheat traits plant area index (PAI), nitrogen yield (NY), canopy water content (CWC), and above-ground dry matter (AGDM). Four ANN-based RTM inversion models were setup, which varied in their spectral resolution, hyperspectral or multispectral, and the inclusion or exclusion of background soil spectra correction. The models were also compared to a simple vegetation index approach using Normalized Difference Vegetation Index (NDVI) and Normalized Difference Red-Edge (NDRE). The RTM inversion model with hyperspectral input data and background soil spectra correction was the best among all tested models for estimating wheat traits during the vegetative developmental stages (PAI: R² = 0.930, RRMSE = 17.9%; NY: R² = 0.908, RRMSE = 14.4%; CWC: R² = 0.967, RRMSE = 17.0%) as well as throughout the whole growing season (PAI: R² = 0.845, RRMSE = 27.7%; CWC: R² = 0.884, RRMSE = 20.0%; AGDM: R² = 0.960, RRMSE = 13.7%). Many models presented in this study provided suitable estimations of the relevant wheat traits PAI, NY, CWC, and AGDM for application in agronomy, breeding, and crop sciences in general. Full article

Hyperspectral remote sensing is crucial due to its continuous spectral information, especially in the quantitative remote sensing (QRS) field. Surface reflectance (SR), a fundamental product in QRS, can play a pivotal role in application accuracy and serves as a key indicator of sensor performance. However, the distinctive spectral characteristics of a hyperspectral image (HSI) make it particularly susceptible to noise during the process of imaging, which inevitably degrades data quality and reduces SR accuracy. Moreover, the validation of hyperspectral SR faces challenges due to the scarcity of reliable validation data. To address these issues, aiming at fast and efficient processing of Chinese domestic ZY1-02D hyperspectral level-1 data, this study proposes a comprehensive processing framework: (1) To address the low efficiency of traditional bad line detection by visual examination, an automatic bad line detection method based on the pixel grayscale gradient threshold algorithm is proposed; (2) A spectral correlation-based interpolation method is developed to overcome the poor performance of adjacent-column averaging in repairing wide bad lines; (3) A reliable validation method was established based on the spectral band adjustment factors method to compare hyperspectral SR with multispectral SR and in-situ ground measurements. The results and analysis demonstrate that the proposed method improves the accuracy of ZY1-02D SR and the method ensures high processing efficiency, requiring only 5 min per scene of ZY1-02D HSI. This study provides a technical foundation for the application of ZY1-02D HSIs and offers valuable insights for the development and enhancement of next-generation hyperspectral sensors. Full article

In order to analyze the relationship between hyperspectral image and soybean canopy nitrogen content in the field, and to establish a prediction model for soybean canopy nitrogen content with few parameters and a simple structure, hyperspectral image data and corresponding nitrogen content data of soybean canopy at different growth periods under different fertilization treatments were acquired. Three spectral characteristic variables selection methods, including correlation coefficient analysis, stepwise regression, and spectral index analysis, were used to determine the spectral characteristic variables that are closely related to the soybean canopy nitrogen content. The predictive models for soybean canopy nitrogen content based on spectral characteristic variables were established using a multiple linear regression algorithm. On this basis, the established prediction models for soybean canopy nitrogen content were compared and analyzed, and the optimal prediction model for soybean canopy nitrogen content was determined. To verify the applicability of prediction models for soybean canopy nitrogen content, a spatial distribution map of soybean canopy nitrogen content at the regional scale was drawn based on unmanned aerial vehicle (UAV) hyperspectral imaging data at the flowering and seed filling stages of soybean in the experimental area, and the spatial distribution of soybean nitrogen content was statistically analyzed. The results show the following: (1) Soybean canopy spectral reflectance was highly significantly negatively correlated with soybean canopy nitrogen content in the range of 450–729 nm, and highly significantly positively correlated in the range of 756–774 nm, with the largest positive correlation coefficient of 0.2296 at 765 nm and the largest absolute value of negative correlation coefficient of −0.8908 at 630 nm. (2) The predictive model for soybean canopy nitrogen content based on three optimal spectral indices, NDSI(R₅₅₂,R₅₅₅), RSI(R₅₃₇,R₅₇₃), and DSI(R₅₄₀,R₅₅₅), was optimal, with R² of 0.9063 and 0.91566 and RMSE of 3.3229 and 3.2219 for the calibration and prediction set, respectively. (3) Based on the established optimal prediction model for soybean canopy nitrogen content combined with the UAV hyperspectral image data, spatial distribution maps of soybean nitrogen content at the flowering and seed filling stages were generated, and the R² between soybean nitrogen content in the spatial distribution map and the ground measured value was 0.93906, the RMSE was 3.6476, and the average relative error was 9.5676%, which indicates that the model had higher prediction accuracy and applicability. (4) The overall results show that the optimal prediction model for soybean canopy nitrogen content established based on hyperspectral imaging data has the characteristics of few parameters, a simple structure, and strong applicability, which provides a new method for realizing rapid, dynamic, and non-destructive monitoring of soybean nutritional status on the regional scale and provides a decision-making basis for precision fertilization management during soybean growth. Full article

The Dead Sea is one of the most saline terminal lakes on Earth, and few organisms survive in this harsh environment. In some onshore spring pools, active and diverse microbial communities flourish. In the geological past, microbial-rich environments left their marks in the form of stromatolites. Stromatolites are studied to better understand the appearance of life on Earth and potentially on other planets. Hyperspectral methodologies have been shown to be useful for detecting structures in stromatolites. In an effort to characterize the biosignatures and chemical composition inherent to stromatolites, we created a spectral classification scheme for distinguishing between stromatolites and their bedrock environment—typically carbonatic rocks, mostly dolomites. The overarching aim comprises the development of an automated hyperspectral reflectance method for detecting the presence of stromatolites. We collected and measured 82 field samples with an ASD spectrometer and used our spectral dataset to train three machine learning algorithms (linear regression, K-Nearest Neighbor, XGBoost). The results show the successful detection of stromatolites, with all three prediction methods giving high accuracy rates (stromatolite > 0.9, bedrock dolomite > 0.8). The continuum removal and spectral ratio technique results identified two significant spectral regions, ~1900 nm (water) and ~2310–2320 nm (carbonates), that allow one to differentiate between stromatolites and dolomites. This study establishes the grounds for the automated detection of a fossilized livable environment in a carbonatic terrain based on its hyperspectral reflectance data. The results have significant implications for future mapping efforts and emphasize the feasibility of automated mapping, extending the data acquisition to airborne or satellite-based hyperspectral remote sensing technologies to detect life forms in extreme environments. Full article

This study addresses the critical need for radiometrically accurate and consistent hyperspectral data as the remote sensing community moves towards a hyperspectral world. Previous calibration efforts on Hyperion, the first on-orbit hyperspectral sensors, have exhibited temporal stability and absolute accuracy limitations. This work has developed and validated a novel cross-calibration methodology to address these challenges. Also, this work adds two other hyperspectral sensors, DLR Earth Sensing Imaging Spectrometer (DESIS) and Earth Surface mineral Dust Source Investigation instrument (EMIT), to maintain temporal continuity and enhance spatial coverage along with spectral resolution. The study established a robust approach for calibrating Hyperion using DESIS and EMIT. The methodology involves several key processes. First is a temporal stability assessment on Extended Pseudo Invariant Calibration Sites (EPICS) Cluster13–Global Temporal Stable (GTS) over North Africa (Cluster13–GTS) using Landsat Sensors Landsat 7 (ETM+), Landsat 8 (OLI). Second, a temporal trend correction model was developed for DESIS and Hyperion using statistically selected models. Third, absolute calibration was developed for DESIS and EMIT using multiple vicarious calibration sites, resulting in an overall absolute calibration uncertainty of 2.7–5.4% across the DESIS spectrum and 3.1–6% on non-absorption bands for EMIT. Finally, Hyperion was cross-calibrated using calibrated DESIS and EMIT as reference (with traceability to ground reference) with a calibration uncertainty within the range of 7.9–12.9% across non-absorption bands. The study also validates these calibration coefficients using OLI over Cluster13–GTS. The validation provided results suggesting a statistical similarity between the absolute calibrated hyperspectral sensors mean TOA (top-of-atmosphere) reflectance with that of OLI. This study offers a valuable contribution to the community by fulfilling the above-mentioned needs, enabling more reliable intercomparison, and combining multiple hyperspectral datasets for various applications. Full article

The ongoing advancement of unmanned aerial vehicles (UAVs) and the evolution of small-scale cameras have bridged the gap between traditional ground-based surveys and orbital sensors. However, these systems present challenges, including limited coverage area, image stabilization constraints, and complex image processing. In water quality monitoring, these difficulties are further compounded by sun glint effects, which hinder the construction of accurate orthomosaics in homogeneous water surfaces and affect radiometric accuracy. This study focuses on evaluating these challenges by comparing two distinct airborne imaging platforms with different spectral resolutions, emphasizing Total Suspended Solids (TSS) monitoring. Hyperspectral airborne surveys were undertaken utilizing a pushbroom system comprising 276 bands, whereas multispectral airborne surveys were conducted employing a global shutter frame with 4 bands. Fifteen aerial survey campaigns were carried out over water bodies from two biomes in Brazil (Amazon and Savanna), at varying concentrations of TSS (0.6–130.7 mg L⁻¹, N: 53). Empirical models using near-infrared channels were applied to accurately monitor TSS in all areas (Hyperspectral camera—RMSE = 3.6 mg L⁻¹, Multispectral camera—RMSE = 9.8 mg L⁻¹). Furthermore, a key contribution of this research is the development and application of Sun Glint mitigation techniques, which significantly improve the reliability of airborne reflectance measurements. By addressing these radiometric challenges, this study provides critical insights into the optimal UAV platform for TSS monitoring in inland waters, enhancing the accuracy and applicability of airborne remote sensing in aquatic environments. Full article

Accurate spectral and radiometric calibration is critical for precise Solar Spectral Irradiance (SSI) and Aerosol Optical Depth (AOD) retrievals in ground-based observations. This study introduces a pixel-based real-time noise deduction method and evaluates its performance using laser sources, Fraunhofer dark lines, and an improved Langley plot calibration. The proposed approach addresses challenges in long-term field SSI monitoring, including spectral noise variation and frequent calibration requirements for wavelength and responsivity corrections. The pixel-based noise deduction method effectively suppresses spectral dark noise to 0 ± 0.890, outperforming temperature-based corrections by 0.6%. Wavelength accuracy tests with laser sources and Fraunhofer dark lines demonstrate high consistency, with δλ < 0.3 nm, while spectral calibration uncertainty is assessed at 0.195 nm to 0.299 nm. The improved Langley plot achieves spectral responsivity differing by only 0.80% from the standard Langley plot and enhances AOD correlation with CE318 by 0.9–2.7% (RMSE: 0.002–0.003), significantly improving AOD observation accuracy. This work advances the development of field SSI hyperspectral observation and calibration, improving the accuracy of SSI and AOD measurements and contributing to the study of environmental changes and climate dynamics. Full article

This study presents the selection of 20 Extended Pseudo Invariant Calibration Sites (EPICS) for radiometric calibration and the derivation of their hyperspectral profiles using the DLR Earth Sensing Imaging Spectrometer (DESIS) and Hyperion data. The hyperspectral profile of one of these clusters, the GONA-EPICS cluster, was validated against ground truth measurements from the RadCalNet Gobabeb Namibia (GONA) site, demonstrating statistical agreement within their respective uncertainties through Welch’s test. The applicability of these hyperspectral profiles was further evaluated by generating Spectral Band Adjustment Factor (SBAF) between Landsat 8 and Sentinel-2A using the GONA-EPICS hyperspectral profile and comparing them to SBAF values derived from RadCalNet GONA site measurements. SBAF results were statistically the same, while SBAF derived from the combined DESIS and Hyperion data exhibited reduced uncertainty compared to those derived using Hyperion data alone, which is attributed to DESIS’s finer spectral resolution (2.5 nm vs. 10 nm). To assess EPICS applicability in cross-calibration, Cluster 13-GTS, which includes pixels from the Libya 4 CNES ROI, was used as a target. Cross-calibration gains obtained using EPICS and the T2T cross-calibration methodology were compared to those from the traditional cross-calibration approach using Libya 4 CNES ROI. Results demonstrated statistically similar gains, with EPICS achieving an uncertainty better than 6% across all bands compared to 4.4% for the traditional method, while enabling global coverage for daily cross-calibration opportunities. This study introduces globally distributed EPICS with validated hyperspectral profiles, offering enhanced spectral resolution and reliability for radiometric calibration and stability monitoring. The methodology supports efficient global scale sensor calibration and prepares for future hyperspectral missions. Full article

Airborne longwave-infrared (LWIR) hyperspectral imagery acquisitions were coordinated with stationary and mobile ground-based in situ measurements of atmospheric ammonia in regions surrounding California’s Salton Sea, an area of commingled intensive animal husbandry and agriculture operations that is encumbered by exceptionally high levels of persistent ammonia and PM_2.5 pollution. The goal of this study was to validate remotely sensed ammonia retrievals against ground truth measurements as part of a broader effort to elucidate the behavior of the atmospheric ammonia burden in this area of abundant diffuse and point sources. The nominal 2 m pixel size of the airborne data revealed variability in ammonia concentrations at a diversity of scales within the study area. At this pixel resolution, ammonia plumes emitted by individual facilities could be clearly discriminated and their dispersion characteristics inferred. Several factors, including thermal contrast and atmospheric boundary layer depth, contributed to the overall uncertainty of the intercomparison between airborne ammonia quantitative retrievals and the corresponding in situ measurements, for which agreement was in the 16–37% range under the most favorable conditions. Hence, while the findings attest to the viability of airborne LWIR spectral imaging for quantifying atmospheric ammonia concentrations, the accuracy of ground-level estimations depends significantly on precise knowledge of these atmospheric factors. Full article

While satellite-based remote sensing offers a promising avenue for large-scale LCC estimations, the accuracy of evaluations is often decreased by mixed pixels, attributable to distinct farming practices and diverse soil conditions. To overcome these challenges and to account for maize intercropping with soybeans at different growth stages combined with varying soil backgrounds, a hyperspectral database for maize was set up using a random linear mixed model applied to hyperspectral data recorded by an unmanned aerial vehicle (UAV). Four methods, namely, Euclidean distance, Minkowski distance, Manhattan distance, and Cosine similarity, were used to compare vegetation spectra from Sentinel-2A with the newly constructed database. In a next step, widely used vegetation indices such as NDVI, NAOC, and CAI were tested to find the optimum method for LCC retrieval, validated by field measurements. The results show that the NAOC had the strongest correlation with ground sampling information (R² = 0.83, RMSE = 0.94 μg/cm², and MAE = 0.67 μg/cm²). Additional field measurements sampled at other farming areas were applied to validate the method’s transferability and generalization. Here too, validation results showed a highly precise LCC estimation (R² = 0.93, RMSE = 1.10 μg/cm², and MAE = 1.09 μg/cm²), demonstrating that integrating UAV hyperspectral data with a random linear mixed model significantly improves satellite-based LCC retrievals. Full article

Hyperspectral imagery and advanced classification techniques can significantly enhance remote sensing’s role in forest monitoring. Thanks to recent missions, such as the Italian Space Agency’s PRISMA (PRecursore IperSpettrale della Missione Applicativa—Hyperspectral PRecursor of the Application Mission), hyperspectral data in narrow bands spanning visible/near infrared to shortwave infrared are now available. In this study, hyperspectral data from PRISMA were used with the aim of testing the applicability of PRISMA with different band sizes to classify tree species in highly biodiverse forest environments. The Serre Regional Park in southern Italy was used as a case study. The classification focused on forest category classes based on the predominant tree species in sample plots. Ground truth data were collected using a global positioning system together with a smartphone application to test its contribution to facilitating field data collection. The final result, measured on a test dataset, showed an F1 greater than 0.75 for four classes: fir (0.81), pine (0.77), beech (0.90), and holm oak (0.82). Beech forests showed the highest accuracy (0.92), while chestnut forests (0.68) and a mixed class of hygrophilous species (0.69) showed lower accuracy. These results demonstrate the potential of hyperspectral spaceborne data for identifying trends in spectral signatures for forest tree classification. Full article

In the past decades, satellite hyperspectral remote sensing instruments have been providing key measurements for environmental monitoring, such as the analysis of water and air quality, soil usage, weather forecasting, or climate change. The success of this technology, however, relies on an accurate knowledge of the instrument’s spectral response functions (SRFs). Usually, the SRFs are assessed on-ground and then monitored on-flight using tedious analysis of the acquired radiances coupled with instrumental models; nonetheless, the complete retrieval of the SRFs is generally out of reach. In this context, EUMETSAT has developed a novel SRF retrieval methodology, with the intention of applying it routinely to the current Metop IASI instruments and soon to Metop-SG IASI-NG, and MTG-S IRS. By making use of spatiotemporal colocations of different detectors within a single instrument or between different platforms, relative SRFs may be retrieved on-flight without any a priori knowledge. The presented methodology is suited for instruments acquiring radiances with contiguous sampling over large spectral bands as the SRFs are retrieved by analyzing the neighboring channels’ correlations. This article focuses on Fourier transform spectrometers (FTS) in the far infrared as they possess these characteristics per design, but it is believed that the method could be extended to other technology and spectral bands. The SRFs are further processed to evaluate the relative self-apodization functions (SAFs), as they represent the discrepancies between the detectors at the interferograms level, the primary measurements of FTS. The following article presents both simulations and applications of the SRF retrieval for the three IASI instruments aboard the Metop platforms of the EPS program. We analyze both IASI sensors aboard Metop-B and C as well as the evolution of Metop-A IASI over 13 years of operation. Full article