In classification of satellite images acquired over smallholder agricultural landscape with complex spectral profiles of various crop types, exploring image spatial information is important. The deep convolutional neural network (CNN), originally designed for natural image recognition in the computer vision field, can automatically explore high level spatial information and thus is promising for such tasks. This study tried to evaluate different CNN structures for classification of four smallholder agricultural landscapes in Heilongjiang, China using pan-sharpened 2 m GaoFen-1 (meaning high resolution in Chinese) satellite images. CNN with three pooling strategies: without pooling, with max pooling and with average pooling, were evaluated and compared with random forest. Two different numbers (~70,000 and ~290,000) of CNN learnable parameters were examined for each pooling strategy. The training and testing samples were systematically sampled from reference land cover maps to ensure sample distribution proportional to the reference land cover occurrence and included 60,000–400,000 pixels to ensure effective training. Testing sample classification results in the four study areas showed that the best pooling strategy was the average pooling CNN and that the CNN significantly outperformed random forest (2.4–3.3% higher overall accuracy and 0.05–0.24 higher kappa coefficient). Visual examination of CNN classification maps showed that CNN can discriminate better the spectrally similar crop types by effectively exploring spatial information. CNN was still significantly outperformed random forest using training samples that were evenly distributed among classes. Furthermore, future research to improve CNN performance was discussed.

Tight junction proteins are correlated with cancer development. As the pivotal proteins in epithelial cells, altered expression and distribution of different claudins have been reported in a wide variety of human malignancies. We have previously reported that claudin-7 was strongly expressed in benign bronchial epithelial cells at the cell-cell junction while expression of claudin-7 was either altered with discontinued weak expression or completely absent in lung cancers. Based on these results, we continued working on the expression pattern of claudin-7 and its relationship with lung cancer development. We herein proposed a new Digital Image Classification, Fragmentation index, Morphological analysis (DICFM) method for differentiating the normal lung tissues and lung cancer tissues based on the claudin-7 immunohistochemical staining. Seventy-seven lung cancer samples were obtained from the Second Affiliated Hospital of Zhejiang University and claudin-7 immunohistochemical staining was performed. Based on C++ and Open Source Computer Vision Library (OpenCV, version 2.4.4), the DICFM processing module was developed. Intensity and fragmentation of claudin-7 expression, as well as the morphological parameters of nuclei were calculated. Evaluation of results was performed using Receiver Operator Characteristic (ROC) analysis. Agreement between these computational results and the results obtained by two pathologists was demonstrated. The intensity of claudin-7 expression was significantly decreased while the fragmentation was significantly increased in the lung cancer tissues compared to the normal lung tissues and the intensity was strongly positively associated with the differentiation of lung cancer cells. Moreover, the perimeters of the nuclei of lung cancer cells were significantly greater than that of the normal lung cells, while the parameters of area and circularity revealed no statistical significance. Taken together, our DICFM approach may be applied as an appropriate approach to quantify the immunohistochemical staining of claudin-7 on the cell membrane and claudin-7 may serve as a marker for identification of lung cancer.

To address the escalating urban heat stress driven by global warming and rapid urbanization, this study integrates multi-source remote sensing data to assess the spatiotemporal dynamics of summer thermal comfort across the Yangtze River Delta Urban Agglomeration (YRDUA) from 2000 to 2020. By combining 2D landscape pattern metrics with 3D building morphological features, this study employs an XGBoost model enhanced with SHAP and PDP techniques to reveal the nonlinear and threshold effects of landscape configurations on the Universal Thermal Climate Index (UTCI). The results show the following: (1) during the study period, over 90% of the region experienced strong or extreme heat stress, and 76.8% of the area exhibited a rising UTCI trend, with an average increase of 0.09 °C per year; (2) forest coverage exceeding 50% reduced the UTCI by approximately 2.5 °C, and an increased water area lowered the UTCI by around 1.5 °C, while highly clustered cropland intensified the UTCI by about 1.5 °C; and (3) a moderate increase in building height and shape complexity improved ventilation and shading, reducing the UTCI by roughly 0.5 °C. These findings highlight that optimizing the blue–green infrastructure and 3D urban form are effective strategies to mitigate urban heat stress, offering scientific guidance for sustainable urban planning.