Search

Seagrass beds play a vital ecological role by regulating climate, maintaining biodiversity, and sequestering carbon. Achieving accurate classification of seagrass beds across both time and space is of significant importance for efficient monitoring. This paper addresses the challenges of seagrass bed classification in remote sensing imagery and the difficulty of achieving temporal and spatial transferability of classification model. Leveraging a long-term Landsat satellite image time series spanning from 1976 to 2022 in the Yellow River Delta, we enhance the DeepLab V3+ network and propose a cross-temporal-spatial domain seagrass bed transfer learning classification approach. We utilize selectively chosen images from a few years in partial regions for training, introduce freeze-training and-unfreeze-training during the model training phase, and then transfer the model to achieve cross-temporal and cross-temporal-spatial domain classification on images from other years and regions. Additionally, we discuss the factors influencing the classification results. The research results indicate that: (1)The method we proposed has shown good results, achieving classification accuracy of 83.17% and 80.99% for seagrass beds in both cross-temporal and cross-temporal-spatial domains. (2) The classification results indicate that this method achieves an average classification accuracy higher by 16.18% compared to networks such as UNet, PSPNet, HRNet, UNet++, SegFormer, etc. under cross-temporal conditions and higher by 17.56% under cross-spatiotemporal conditions for seagrass bed classification. (3) Based on the classification results, it is observed that from 1973 to 1986, the overall area of seagrass beds in the Yellow River Delta had an initial growth trend, with the largest seagrass bed area recorded in 1986, reaching 4281.289 hectares. Subsequently, the seagrass beds showed an overall decreasing trend, and by 2019 they had almost completely disappeared. The cross-temporal-spatial domain seagrass bed transfer learning classification method proposed in this paper can provide valuable support for the monitoring, restoration, management, and utilization of seagrass ecosystems. [ABSTRACT FROM AUTHOR]

Coal is a prominent energy resource in China. Therefore, it is crucial to accurately extract the coal-covered areas. Taking Xinjiang's Zhundong mining region as the study area, Landsat 8 OLI data were employed to assess the spectral curves of four typical ground objects, including vegetation, bare land, water body and bare coal. The Normalized Difference Bare Coal Index (NDBCI) and the Normalized Difference Coal Index (NDCI) were developed to extract coal-covered area. Higher-resolution Sentinel-2B data for the same period were used for verification, with extraction accuracy evaluated by five metrics including Kappa coefficient, Overall accuracy, Checking accuracy, Checking completeness and F1-score. The results of extracting coal-covered areas showed that (1) the NDBCI showed 'internal fragmentation' and the NDCI demonstrated 'pixel overflow' during the extraction process. Therefore, we determined the optimal thresholds −0.03 for NDBCI and 0.04 for NDCI. (2) NDBCI distinguished pixels with lower grey-scale values, such as water body, road and gangue. However, some dump zones and shed patches were misclassified. (3) NDCI generated clear boundaries and more complete interiors, and the dump zone and shed could be distinguished. However, some water body parts were misclassified as coal-covered areas. (4) Combined application of NDBCI and NDCI generated a 'complementary' effect better than both individual modes. Kappa coefficient, Overall accuracy and F1-score reached 0.95, 98.76% and 0.75, respectively. This study successfully extracted coal-covered areas by developing a remote sensing index based on spectral traits and a priori knowledge of the study area. The proposed combined extraction mode achieved high accuracy for rapid and reliable identification of coal-covered areas. Highlights: Two new remote sensing indexes for coal-covered area extraction were proposed in this paper. Complementary advantages were found between NDBCI and NDCI in the extraction. Accuracy assessment was performed based on manually deciphered high-precision raster data. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of training deep learning models for fire smoke scene detection from multi-sensor, multi-spectral satellite imagery, where spectral bands vary and training data is scarce, especially for new sensors. We introduce a novel cross-sensor transfer learning approach enhanced by spectral pattern extraction, notably aided by a deep learning (DL) module called Input Amplification (IA). Our contribution includes the creation of two datasets, Landsat_smk2770 and Sentinel2_smk, with varying spectral bands. We employ a model named IA_VIB_SD which incorporates IA and is designed specifically for fire smoke scene detection. We investigated the transferability of the Landsat_smk2770-trained IA_VIB_SD model to the Sentinel2_smk dataset using various transfer learning techniques, and compared the performance of the transferred model with the benchmark IA_VIB_SD model exclusively trained on pure Sentinel2_smk data. Our proposed transfer learning approach resulted in a transferred model with an average accuracy 5% higher than the benchmark model. Notably, Our proposed transfer learning approach outperformed existing transfer learning methods by more than 1% in terms of the accuracy, even when trained on a mere 10% of the Sentinel2_smk dataset. This research advances fire smoke scene detection from multi-sensor, multi-spectral satellite imagery. [ABSTRACT FROM AUTHOR]