Yellow rust in winter wheat is a widespread and serious fungal disease, resulting in significant yield losses globally. Effective monitoring and accurate detection of yellow rust are crucial to ensure stable and reliable wheat production and food security. The existing standard methods often rely on manual inspection of disease symptoms in a small crop area by agronomists or trained surveyors. This is costly, time consuming and prone to error due to the subjectivity of surveyors. Recent advances in unmanned aerial vehicles (UAVs) mounted with hyperspectral image sensors have the potential to address these issues with low cost and high efficiency. This work proposed a new deep convolutional neural network (DCNN) based approach for automated crop disease detection using very high spatial resolution hyperspectral images captured with UAVs. The proposed model introduced multiple Inception-Resnet layers for feature extraction and was optimized to establish the most suitable depth and width of the network. Benefiting from the ability of convolution layers to handle three-dimensional data, the model used both spatial and spectral information for yellow rust detection. The model was calibrated with hyperspectral imagery collected by UAVs in five different dates across a whole crop cycle over a well-controlled field experiment with healthy and rust infected wheat plots. Its performance was compared across sampling dates and with random forest, a representative of traditional classification methods in which only spectral information was used. It was found that the method has high performance across all the growing cycle, particularly at late stages of the disease spread. The overall accuracy of the proposed model (0.85) was higher than that of the random forest classifier (0.77). These results showed that combining both spectral and spatial information is a suitable approach to improving the accuracy of crop disease detection with high resolution UAV hyperspectral images.

Computer-aided early diagnosis of Alzheimer's disease (AD) and its prodromal form mild cognitive impairment (MCI) based on structure Magnetic Resonance Imaging (sMRI) has provided a cost-effective and objective way for early prevention and treatment of disease progression, leading to improved patient care. In this work, we have proposed a novel computer-aided approach for early diagnosis of AD by introducing an explainable 3D Residual Attention Deep Neural Network (3D ResAttNet) for end-to-end learning from sMRI scans. Different from the existing approaches, the novelty of our approach is three-fold: 1) A Residual Self-Attention Deep Neural Network has been proposed to capture local, global and spatial information of MR images to improve diagnostic performance; 2) An explanation method using Gradient-based Localization Class Activation mapping (Grad-CAM) has been introduced to improve the explainable of the proposed method; 3) This work has provided a full end-to-end learning solution for automated disease diagnosis. Our proposed 3D ResAttNet method has been evaluated on a large cohort of subjects from real datasets for two changeling classification tasks (i.e., Alzheimer's disease (AD) vs. Normal cohort (NC) and progressive MCI (pMCI) vs. stable MCI (sMCI)). The experimental results show that the proposed approach has a competitive advantage over the state-of-the-art models in terms of accuracy performance and generalizability. The explainable mechanism in our approach is able to identify and highlight the contribution of the important brain parts (e.g., hippocampus, lateral ventricle and most parts of the cortex) for transparent decisions.

Land cover information plays an important role in mapping ecological and environmental changes in Earth’s diverse landscapes for ecosystem monitoring. Remote sensing data have been widely used for the study of land cover, enabling efficient mapping of changes of the Earth surface from Space. Although the availability of high-resolution remote sensing imagery increases significantly every year, traditional land cover analysis approaches based on pixel and object levels are not optimal. Recent advancement in deep learning has achieved remarkable success on image recognition field and has shown potential in high spatial resolution remote sensing applications, including classification and object detection. In this paper, a comprehensive review on land cover classification and object detection approaches using high resolution imagery is provided. Through two case studies, we demonstrated the applications of the state-of-the-art deep learning models to high spatial resolution remote sensing data for land cover classification and object detection and evaluated their performances against traditional approaches. For a land cover classification task, the deep-learning-based methods provide an end-to-end solution by using both spatial and spectral information. They have shown better performance than the traditional pixel-based method, especially for the categories of different vegetation. For an objective detection task, the deep-learning-based object detection method achieved more than 98% accuracy in a large area; its high accuracy and efficiency could relieve the burden of the traditional, labour-intensive method. However, considering the diversity of remote sensing data, more training datasets are required in order to improve the generalisation and the robustness of deep learning-based models.

Rice is a staple food in East Asia and Southeast Asia—an area that accounts for more than half of the world’s population, and 11% of its cultivated land. Studies on rice monitoring can provide direct or indirect information on food security, and water source management. Remote sensing has proven to be the most effective method for the large-scale monitoring of croplands, by using temporary and spectral information. The Google Earth Engine (GEE) is a cloud-based platform providing access to high-performance computing resources for processing extremely large geospatial datasets. In this study, by leveraging the computational power of GEE and a large pool of satellite and other geophysical data (e.g., forest and water extent maps, with high accuracy at 30 m), we generated the first up-to-date rice extent map with crop intensity, at 10 m resolution in the three provinces with the highest rice production in China (the Heilongjiang, Hunan and Guangxi provinces). Optical and synthetic aperture radar (SAR) data were monthly and metric composited to ensure a sufficient amount of up-to-date data without cloud interference. To remove the common confounding noise in the pixel-based classification results at medium to high resolution, we integrated the pixel-based classification (using a random forest classifier) result with the object-based segmentation (using a simple linear iterative clustering (SLIC) method). This integration resulted in the rice planted area data that most closely resembled official statistics. The overall accuracy was approximately 90%, which was validated by ground crop field points. The F scores reached 87.78% in the Heilongjiang Province for monocropped rice, 89.97% and 80.00% in the Hunan Province for mono- and double-cropped rice, respectively, and 88.24% in the Guangxi Province for double-cropped rice.

Land cover classification data have a very important practical application value, and long time series land cover classification datasets are of great significance studying environmental changes, urban changes, land resource surveys, hydrology and ecology. At present, the starting point of continuous land cover classification products for many years is mostly after the year 2000, and there is a lack of long-term continuously annual land cover classification products before 2000. In this study, a long time series classification data extraction model is established using a bidirectional long-term and short-term memory network (Bi-LSTM). In the model, quantitative remote sensing products combined with DEM, nighttime lighting data, and latitude and longitude elevation data were used. We applied this model in China and obtained China’s 1982–2017 0.05° land cover classification product. The accuracy assessment results of the test data show that the overall accuracy is 84.2% and that the accuracies of wetland, water, glacier, tundra, city and bare soil reach 92.1%, 92.0%, 94.3%, 94.6% and 92.4%, respectively. For the first time, this study used a variety of long time series data, especially quantitative remote sensing products, for the classification of features. At the same time, it also acquired long time series land cover classification products, including those from the year 2000. This study provides new ideas for the establishment of higher-resolution long time series land cover classification products.