Geological remote sensing interpretation can extract elements of interest from multiple types of images, which is vital in geological survey and mapping, especially in inaccessible regions. However, due to numerous classes, high interclass similarities, complex distributions, and sample imbalances of geological elements, the interpretation results of machine learning (ML)-based methods are understandably worse than manual visual interpretation. In addition, scholars in remote sensing have mainly carried out their works to interpret a single geological element category, such as mineral, lithological, soil, and structure. The interpretation of multiple geological elements is missing, which is more in line with the open world. To improve the interpretation results of ML-based methods and reduce the labor cost in geological survey and mapping, we propose a deep learning (DL)-feature-based adaptive multisource data fusion network (AMSDFNet) for the efficient interpretation of multiple geological remote sensing elements. The AMSDFNet has two branches for learning valuable spatial and spectral information from two kinds of data sources, in which the atrous spatial pyramid pooling (ASPP) operation and an attention block are applied to adaptively extract and fuse multiscale informative features. A hard example mining algorithm was also added to select important training examples to address sample imbalance. A large-scale region in western China with sufficient geological elements was set as the research area. The proposed model improved the two critical metrics by about 2% in the experiment section. As far as we know, this research work is the first time DL features and multisource remote sensing images have been utilized to simultaneously interpret geological elements of lithology, soil, surface water, and glaciers. The extensive experimental results demonstrated the superiority of DL features and our model in geological remote sensing interpretation.
23 February 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Accurate bathymetric maps are essential to understand marine and coastal ecosystems. With the development of satellite and sensor technology, satellite-derived bathymetry (SDB) has been widely used to measure the depth of nearshore waters. Employment of physics-based methods requires a series of optical parameters of the water column and seafloor, which limits the application of these methods to shallow-water bathymetry. Due to convenience, low costs, and high efficiency, empirical methods based on in situ measurements and satellite imagery are increasingly used for nearshore bathymetry. These measurements are required to calibrate empirical models, so that reasonable accuracy can be achieved. The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), equipped with the advanced topographic laser altimeter system, provides a novel opportunity for nearshore bathymetry. Using the new measurement strategy of photon counting, ICESat-2 can provide accurate bathymetric points from spaceborne observations, which can be used in place of in situ water depth data. In this study, ICESat-2 bathymetric points and multispectral images were used to train four typical models and produce bathymetric maps for Shanhu Island, Ganquan Island, and Lingyang Reef in the Xisha Islands of China. We evaluated the bathymetric results by comparing them with reference depth data from airborne light detection and ranging. All models had a satisfactory accuracy, as well as multimodel and multisource image consistency. With the ICESat-2 bathymetric points, SDB is no longer limited by in situ measurements. Hence, this approach could be extended to a larger scale to obtain nearshore bathymetric maps of coastal areas, surrounding islands, and reefs using free and open-access satellite data.
13 July 2023 in ISPRS Journal of Photogrammetry and Remote Sensing
Two novel and high-throughput enzyme-linked immunosorbent assays (ELISA) were developed for determining tonalide in human blood samples. For establishing the proposed methods, the tonalide hapten and immunogen primarily were prepared. After the immunization, the polyclonal antibody and biotinylated polyclonal antibody were obtained. The biotin-streptavidin system and polyamidoamine-gold nanoparticle conjugation were applied respectively to establish thebiotin-streptavidin-ELISA and Au-polyamidoamine-ELISA. For reducing the background interference, some factors and procedures were also discussed and optimized. Under the optimal conditions, the IC10 of biotin-streptavidin-ELISA was 0.046 µg/L and the IC10 of Au-polyamidoamine-ELISA was 0.016 µg/L. The Au-polyamidoamine-ELISA was used to determine tonalide in human blood and the recovery values and coefficients of variation were acceptable. In this study, tonalide was detected in 92.2% of the samples; the median and the maximum values were 0.62 and 1.76 µg/L, respectively. In general, due to the specificity of the antibody and novel nanoprobe design, this Au-polyamidoamine-ELISA simplified the sample preparation and provided a useful and potential way for trace determination of tonalide. The results also suggested that tonalide concentrations were not significantly relative to gender, but the high concentrations of tonalide in human blood should encourage further toxicological studies.
Airborne photon‐counting LiDAR has emerged as a promising tool for shallow‐water bathymetry, offering high spatial resolution and penetration depth for coastal and nearshore applications. This study presents an integrated workflow for processing airborne photon‐counting LiDAR data to estimate shallow‐water bathymetry. The workflow combines voxel‐level false discovery rate gating, layer‐wise adaptive clustering, and wave‐driven refraction correction to improve the reliability of depth estimates. The approach was validated using two coastal data sets, representing real‐world conditions with varying water clarity and background noise. Results show that the workflow effectively separates surface, water‐column, and bottom layers, achieving high accuracy in clear‐water conditions at North Reef (RMSE 0.214 and 0.309 m) and operationally useful retrieval in noisier class‐II waters at Weizhou Island (RMSE 1.342 and 1.558 m), where spatial gradients are still preserved within the effective penetration range. This workflow is suitable for operational coastal monitoring and environmental assessment.