Search Results (13)

(1) Background: Wetlands are ecologically significant ecosystems that support biodiversity and contribute to essential environmental functions such as water purification, carbon storage and flood regulation. However, these ecosystems face increasing pressures from land-use change and degradation, prompting the need for scalable and accurate classification methods to support conservation and policy efforts. In this research, our motivation was to test whether high-spatial-resolution PlanetScope imagery can be used with pixel-based machine learning to support the mapping and monitoring of wetlands at a national scale. (2) Methods: This study compared four machine learning classification models—Random Forest (RF), XGBoost (XGB), Histogram-Based Gradient Boosting (HGB) and a Multi-Layer Perceptron Classifier (MLPC)—to detect and map wetland areas across New Zealand. All models were trained using eight-band SuperDove satellite imagery from PlanetScope, with a spatial resolution of ~3 m, and ancillary geospatial datasets representing topography and soil drainage characteristics, each of which is available globally. (3) Results: All four machine learning models performed well in detecting wetlands from SuperDove imagery and environmental covariates, with varying strengths. The highest accuracy was achieved using all eight image bands alongside features created from supporting geospatial data. For binary wetland classification, the highest F1 scores were recorded by XGB (0.73) and RF/HGB (both 0.72) when including all covariates. MLPC also showed competitive performance (wetland F1 score of 0.71), despite its relatively lower spatial consistency. However, each model over-predicts total wetland area at a national level, an issue which was able to be reduced by increasing the classification probability threshold and spatial filtering. (4) Conclusions: The comparative analysis highlights the strengths and trade-offs of RF, XGB, HGB and MLPC models for wetland classification. While all four methods are viable, RF offers some key advantages, including ease of deployment and transferability, positioning it as a promising candidate for scalable, high-resolution wetland monitoring across diverse ecological settings. Further work is required for verification of small-scale wetlands (<~0.5 ha) and the addition of fine-spatial-scale covariates. Full article

Mediterranean subtidal reefs host ecologically significant habitats, including forests of Cystoseira spp., which form complex benthic communities within the photic zone. These habitats are increasingly degraded due to climate change, invasive species, and anthropogenic pressures, particularly in the eastern Mediterranean. In support of habitat monitoring under the EU Natura 2000 directive and the Nature Restoration Regulation, this study investigates the utility of high-resolution satellite remote sensing for mapping subtidal brown algae and associated benthic classes. Using imagery from the SuperDove sensor (Planet Labs, San Francisco, CA, USA), we developed an integrated mapping workflow at the Natura 2000 site GR2420009. Aquatic reflectance was derived using ACOLITE v.20250114.0, and both supervised classification and spectral unmixing were implemented in the EnMAP Toolbox v.3.16.3 within QGIS. A Random Forest classifier (100 fully grown trees) achieved high thematic accuracy across all habitat types (F1 scores: 0.87–1.00), with perfect classification of shallow soft bottoms and strong performance for Cystoseira s.l. (F1 = 0.94) and Seagrass (F1 = 0.93). Spectral unmixing further enabled quantitative estimation of fractional cover, with high predictive accuracy for deep soft bottoms (R² = 0.99; RPD = 18.66), shallow soft bottoms (R² = 0.98; RPD = 8.72), Seagrass (R² = 0.88; RPD = 3.01) and Cystoseira s.l. (R² = 0.82; RPD = 2.37). The lower performance for rocky reefs with other cover (R² = 0.71) reflects spectral heterogeneity and shadowing effects. The results highlight the effectiveness of combining classification and unmixing approaches for benthic habitat mapping using CubeSat constellations, offering scalable tools for large-area monitoring and ecosystem assessment. Despite challenges in field data acquisition, the presented framework provides a robust foundation for remote sensing-based conservation planning in optically shallow marine environments. Full article

This study enhances the accuracy of optical satellite-derived bathymetric datasets in a shallow, mixed-bottom, low-wave-energy coastal environment by identifying the optimal combination of input satellite imagery, spectral bands, and empirical derivation techniques. A total of 109 unique derivations were performed based on an exhaustive combination of these variables. These derivations were calibrated and validated using 1,064,536 ground truth observations. The results revealed that the multiband linear technique consistently outperformed the band ratio technique, achieving the best results with input bands from PlanetScope SuperDove imagery. The top-performing derivation attained an R² value of 0.94 and an RMSE of 0.41 m when compared with the ground truth data, surpassing the published RMSE values in similar environments. Further validation beyond the calibration site confirmed its effectiveness within depths of 0.5 m to 5 m, demonstrating an RMSE of 0.51 m, albeit with a gradual reduction in accuracy with increasing depth. This research not only identifies the optimal combination of variables but also provides valuable insights into how the number of input bands, their spatial resolution, and their specific spectral properties (central wavelength and bandwidth) influence the quality of satellite-derived bathymetry datasets. Challenges remain in accounting for mixed bottom types and their variable albedos. Full article

Water scarcity, exacerbated by climate change and increasing agricultural water demands, highlights the necessity for efficient irrigation management. This study focused on estimating actual evapotranspiration (ETa) in watermelons under semi-arid Mediterranean conditions by integrating high-resolution satellite imagery and agro-meteorological data. Field experiments were conducted in Rutigliano, southern Italy, over a 2.80 ha area. ETa was measured with the eddy covariance (EC) technique and predicted using machine learning models. Multispectral reflectance data from Planet SuperDove satellites and local meteorological records were used as predictors. Partial least squares, the generalized linear model and three machine learning algorithms (Random Forest, Elastic Net, and Support Vector Machine) were evaluated. Random Forest yielded the highest predictive accuracy with an average R² of 0.74, RMSE of 0.577 mm, and MBE of 0.03 mm. Model interpretability was performed through permutation importance and SHAP, identifying the near-infrared and red spectral bands, average daily temperature, and relative humidity as key predictors. This integrated approach could provide a scalable, precise method for watermelon ETa estimation, supporting data-driven irrigation management and improving water use efficiency in Mediterranean horticultural systems. Full article

This study investigated the application of high-resolution satellite imagery from SuperDove satellites combined with machine learning algorithms to estimate the spatiotemporal variability of some winter wheat parameters, including the relative leaf chlorophyll content (RCC), relative water content (RWC), and aboveground dry matter (DM). The research was carried out within an experimental field in Southern Italy during the 2024 growing season. Different machine learning (ML) algorithms were trained and compared using spectral band data and calculated vegetation indices (VIs) as predictors. Model performance was assessed using R² and RMSE. The ML models tested were random forest (RF), support vector regressor (SVR), and extreme gradient boosting (XGB). RF outperformed the other ML algorithms in the prediction of RCC when using VIs as predictors (R² = 0.81) and in the prediction of the RWC and DM when using spectral bands data as predictors (R² = 0.71 and 0.87, respectively). Model explainability was assessed with the SHAP method. A SHAP analysis highlighted that GNDVI, Cl1, and NDRE were the most important VIs for predicting RCC, while yellow and red bands were the most important for DM prediction, and yellow and nir bands for RWC prediction. The best model found for each target was used to model its seasonal trend and produce a variability map. This approach highlights the potential of integrating ML and high-resolution satellite imagery for the remote monitoring of wheat, which can support sustainable farming practices. Full article

The Planet SuperDove sensors produce eight-band, three-meter resolution images covering the blue, green, red, red-edge, and NIR spectral bands. Variations in spectral response in the data used to perform atmospheric correction combined with low signal-to-noise over ocean waters can lead to visible striping artifacts in the downstream ocean-color products. It was determined that the striping artifacts could be removed from these products by filtering the top of the atmosphere radiance in the red and NIR bands prior to selecting the aerosol models, without sacrificing high-resolution features in the imagery. This paper examines an approach that applies this filtering to the respective bands as a preprocessing step. The outcome and performance of this filtering technique are examined to assess the success of removing the striping effect in atmospherically corrected Planet SuperDove data. Full article

Achieving precise and swift monitoring of aquaculture ponds in coastal regions is essential for the scientific planning of spatial layouts in aquaculture zones and the advancement of ecological sustainability in coastal areas. However, because the distribution of many land types in coastal areas and the complex spectral features of remote sensing images are prone to the phenomenon of ‘same spectrum heterogeneous objects’, the current deep learning model is susceptible to background noise interference in the face of complex backgrounds, resulting in poor model generalization ability. Moreover, with the image features of aquaculture ponds of different scales, the model has limited multi-scale feature extraction ability, making it difficult to extract effective edge features. To address these issues, this work suggests a novel semantic segmentation model for aquaculture ponds called MPG-Net, which is based on an enhanced version of the U-Net model and primarily comprises two structures: MS and PGC. The MS structure integrates the Inception module and the Dilated residual module in order to enhance the model’s ability to extract the features of aquaculture ponds and effectively solve the problem of gradient disappearance in the training of the model; the PGC structure integrates the Global Context module and the Polarized Self-Attention in order to enhance the model’s ability to understand the contextual semantic information and reduce the interference of redundant information. Using Sentinel-2 and Planet images as data sources, the effectiveness of the refined method is confirmed through ablation experiments conducted on the two structures. The experimental comparison using the FCN8S, SegNet, U-Net, and DeepLabV3 classical semantic segmentation models shows that the MPG-Net model outperforms the other four models in all four precision evaluation indicators; the average values of precision, recall, IoU, and F1-Score of the two image datasets with different resolutions are 94.95%, 92.95%, 88.57%, and 93.94%, respectively. These values prove that the MPG-Net model has better robustness and generalization ability, which can reduce the interference of irrelevant information, effectively improve the extraction precision of individual aquaculture ponds, and significantly reduce the edge adhesion of aquaculture ponds in the extraction results, thereby offering new technical support for the automatic extraction of aquaculture ponds in coastal areas. Full article

The global increase in wildfires due to climate change highlights the need for accurate wildfire mapping. This study performs a proof of concept on the usefulness of SuperDove imagery for wildfire mapping. To address this topic, we present an automatic methodology that combines the use of various vegetation indices with clustering algorithms (bisecting k-means and k-means) to analyze images before and after fires, with the aim of improving the precision of the burned area and severity assessments. The results demonstrate the potential of using this PlanetScope sensor, showing that the methodology effectively delineates burned areas and classifies them by severity level, in comparison with data from the Copernicus Emergency Management Service (CEMS). Thus, the potential of the SuperDove satellite sensor constellation for fire monitoring is highlighted, despite its limitations regarding radiometric distortion and the absence of Short-Wave Infrared (SWIR) bands, suggesting that the methodology could contribute to better fire management strategies. Full article

Pasture degradation poses significant economic, social, and environmental impacts in the Brazilian savanna ecosystem. Despite these impacts, effectively detecting varying intensities of agronomic and biological degradation through remote sensing remains challenging. This study explores the potential of the eight-band PlanetScope SuperDove satellite constellation to discriminate between five classes of pasture degradation: non-degraded pasture (NDP); pastures with low- (LID) and moderate-intensity degradation (MID); severe agronomic degradation (SAD); and severe biological degradation (SBD). Using a set of 259 cloud-free images acquired in 2022 across five sites located in central Brazil, the study aims to: (i) identify the most suitable period for discriminating between various degradation classes; (ii) evaluate the Random Forest (RF) classification performance of different SuperDove attributes; and (iii) compare metrics of accuracy derived from two predicted scenarios of pasture degradation: a more challenging one involving five classes (NDP, LID, MID, SAD, and SBD), and another considering only non-degraded and severely degraded pastures (NDP, SAD, and SBD). The study assessed individual and combined sets of SuperDove attributes, including band reflectance, vegetation indices, endmember fractions from spectral mixture analysis (SMA), and image texture variables from Gray-level Co-occurrence Matrix (GLCM). The results highlighted the effectiveness of the transition from the rainy to the dry season and the period towards the beginning of a new seasonal rainy cycle in October for discriminating pasture degradation. In comparison to the dry season, more favorable discrimination scenarios were observed during the rainy season. In the dry season, increased amounts of non-photosynthetic vegetation (NPV) complicate the differentiation between NDP and SBD, which is characterized by high soil exposure. Pastures exhibiting severe biological degradation showed greater sensitivity to water stress, manifesting earlier reflectance changes in the visible and near-infrared bands of SuperDove compared to other classes. Reflectance-based classification yielded higher overall accuracy (OA) than the approaches using endmember fractions, vegetation indices, or texture metrics. Classifications using combined attributes achieved an OA of 0.69 and 0.88 for the five-class and three-class scenarios, respectively. In the five-class scenario, the highest F1-scores were observed for NDP (0.61) and classes of agronomic (0.71) and biological (0.88) degradation, indicating the challenges in separating low and moderate stages of pasture degradation. An initial comparison of RF classification results for the five categories of degraded pastures, utilizing reflectance data from MultiSpectral Instrument (MSI)/Sentinel-2 (400–2500 nm) and SuperDove (400–900 nm), demonstrated an enhanced OA (0.79 versus 0.66) with Sentinel-2 data. This enhancement is likely to be attributed to the inclusion of shortwave infrared (SWIR) spectral bands in the data analysis. Our findings highlight the potential of satellite constellation data, acquired at high spatial resolution, for remote identification of pasture degradation. Full article

NASA’s Earth Surface Mineral Dust Source Investigation (EMIT) mission seeks to use spaceborne imaging spectroscopy (hyperspectral imaging) to map the mineralogy of arid dust source regions. Here we apply recent developments in Joint Characterization (JC) and the spectral Mixture Residual (MR) to explore the information content of data from this novel mission. Specifically, for a mosaic of 20 spectrally diverse scenes, we find: (1) a generalized three-endmember (Substrate, Vegetation, Dark; SVD) spectral mixture model is capable of capturing the preponderance (99% in three dimensions) of spectral variance with low misfit (99% pixels with <3.7% RMSE); (2) manifold learning (UMAP) is capable of identifying spatially coherent, physically interpretable clustering relationships in the spectral feature space; (3) UMAP yields results that are at least as informative when applied to the MR as when applied to raw reflectance; (4) SVD fraction information usefully contextualizes UMAP clustering relationships, and vice-versa (JC); and (5) when EMIT data are convolved to spectral response functions of multispectral instruments (Sentinel-2, Landsat 8/9, Planet SuperDove), SVD fractions correlate strongly across sensors, but UMAP clustering relationships for the EMIT hyperspectral feature space are far more informative than for simulated multispectral sensors. Implications are discussed for both the utility of EMIT data in the near-term and for the potential of high signal-to-noise (SNR) spaceborne imaging spectroscopy more generally, to transform the future of optical remote sensing in the years and decades to come. Full article

Green tide beaching events have occurred frequently in the Yellow Sea since 2007, causing a series of ecological and economic problems. Satellite imagery has been widely applied to monitor green tide outbreaks in open water. Traditional satellite sensors, however, are limited by coarse resolution or a low revisit rate, making it difficult to provide timely distribution of information about green tides in the nearshore. In this study, both PlanetScope Super Dove images and unmanned aerial vehicle (UAV) images are used to monitor green tide beaching events on the southern side of Shandong Peninsula, China. A deep learning model (VGGUnet) is used to extract the green tide features and quantify the green tide coverage area or biomass density. Compared with the U-net model, the VGGUnet model has a higher accuracy on the Super Dove and UAV images, with F1-scores of 0.93 and 0.92, respectively. The VGGUnet model is then applied to monitor the distribution of green tide on the beach and in the nearshore water; the results suggest that the VGGUnet model can accurately extract green tide features while discarding other confusing features. By using the Super Dove and UAV images, green tide beaching events can be accurately monitored and are consistent with field investigations. From the perspective of near real-time green tide monitoring, high-resolution imagery combined with deep learning is an effective approach. The findings pave the way for monitoring and tracking green tides in coastal zones, as well as assisting in the prevention and control of green tide disasters. Full article

The monitoring of agronomic parameters like biomass, water stress, and plant health can benefit from synergistic use of all available remotely sensed information. Multispectral imagery has been used for this purpose for decades, largely with vegetation indices (VIs). Many multispectral VIs exist, typically relying on a single feature—the spectral red edge—for information. Where hyperspectral imagery is available, spectral mixture models can use the full VSWIR spectrum to yield further insight, simultaneously estimating area fractions of multiple materials within mixed pixels. Here we investigate the relationships between VIs and mixture models by comparing hyperspectral endmember fractions to six common multispectral VIs in California’s diverse crops and soils. In so doing, we isolate spectral effects from sensor- and acquisition-specific variability associated with atmosphere, illumination, and view geometry. Specifically, we compare: (1) fractional area of photosynthetic vegetation (F_v) from 64,000,000 3–5 m resolution AVIRIS-ng reflectance spectra; and (2) six popular VIs (NDVI, NIRv, EVI, EVI2, SR, DVI) computed from simulated Planet SuperDove reflectance spectra derived from the AVIRIS-ng spectra. Hyperspectral F_v and multispectral VIs are compared using both parametric (Pearson correlation, ρ) and nonparametric (Mutual Information, MI) metrics. Four VIs (NIRv, DVI, EVI, EVI2) showed strong linear relationships with F_v (ρ > 0.94; MI > 1.2). NIRv and DVI showed strong interrelation (ρ > 0.99, MI > 2.4), but deviated from a 1:1 correspondence with F_v. EVI and EVI2 were strongly interrelated (ρ > 0.99, MI > 2.3) and more closely approximated a 1:1 relationship with F_v. In contrast, NDVI and SR showed a weaker, nonlinear, heteroskedastic relation to F_v (ρ < 0.84, MI = 0.69). NDVI exhibited both especially severe sensitivity to unvegetated background (–0.05 < NDVI < +0.6) and saturation (0.2 < F_v < 0.8 for NDVI = 0.7). The self-consistent atmospheric correction, radiometry, and sun-sensor geometry allows this simulation approach to be further applied to indices, sensors, and landscapes worldwide. Full article

A capability for mapping meter-level resolution soil moisture with frequent temporal sampling over large regions is essential for quantifying local-scale environmental heterogeneity and eco-hydrologic behavior. However, available surface soil moisture (SSM) products generally involve much coarser grain sizes ranging from 30 m to several 10 s of kilometers. Hence, a new method is proposed to estimate 3-m resolution SSM using a combination of multi-sensor fusion, machine-learning (ML), and Cumulative Distribution Function (CDF) matching approaches. This method established favorable SSM correspondence between 3-m pixels and overlying 9-km grid cells from overlapping Planet SuperDove (PSD) observations and NASA Soil Moisture Active-Passive (SMAP) mission products. The resulting 3-m SSM predictions showed improved accuracy by reducing absolute bias and RMSE by ~0.01 cm³/cm³ over the original SMAP data in relation to in situ soil moisture measurements for the Australian Yanco region while preserving the high sampling frequency (1–3 day global revisit) and sensitivity to surface wetness (R 0.865) from SMAP. Heterogeneous soil moisture distributions varying with vegetation biomass gradients and irrigation regimes were generally captured within a selected study area. Further algorithm refinement and implementation for regional applications will allow for improvement in water resources management, precision agriculture, and disaster forecasts and responses. Full article