Recently, convolutional neural networks (CNNs) and self-attention mechanisms have been widely applied in plant disease identification tasks, yielding significant successes. Currently, the majority of research models for tomato leaf disease recognition rely solely on traditional convolutional models or Transformer architectures and fail to capture both local and global features simultaneously. This limitation may result in biases in the model’s focus, consequently impacting the accuracy of disease recognition. Consequently, models capable of extracting local features while attending to global information have emerged as a novel research direction. To address these challenges, we propose an Eff-Swin model that integrates the enhanced features of the EfficientNetV2 and Swin Transformer networks, aiming to harness the local feature extraction capability of CNNs and the global modeling ability of Transformers. Comparative experiments demonstrate that the enhanced model has achieved a further increase in training accuracy, reaching an accuracy rate of 99.70% on the tomato leaf disease dataset, which is 0.49~3.68% higher than that of individual network models and 0.8~1.15% higher than that of existing state-of-the-art combined approaches. The results show that integrating attention mechanisms into convolutional models can significantly enhance the accuracy of tomato leaf disease recognition while also offering the great potential of the Eff-Swin backbone with self-attention in plant disease identification.

Cloud contamination greatly limits the potential utilization of optical images for geoscience applications. An effective alternative is to extract data from synthetic aperture radar (SAR) images to remove clouds due to the strong penetration ability of microwaves. In this article, we propose a novel unified spatial–spectral residual network that utilizes SAR images as auxiliary data to remove clouds from optical images. The method can better establish the relationship between SAR and optical images and be divided into two modules: feature extraction and fusion module and reconstruction module. In the feature extraction and fusion module, a gated convolutional layer is introduced to discriminate cloud pixels from clean pixels, which makes up for the lack of distinguishing ability of vanilla convolutional layers and avoids the error of cloud areas in feature extraction. In the reconstruction module, spatial and channel attention mechanisms are introduced to obtain global spatial and spectral information. The network is tested on three datasets with different spatial resolutions and compositions of land covers to verify the effectiveness and applicability of the method. The results show that the method outperforms other mainstream algorithms that simultaneously use SAR images as auxiliary data with a gain of about 2.3 dB in terms of peak signal-to-noise ratio PSNR on the SEN12MS-CR dataset.

Accurately predicting winter wheat yield before harvest could greatly benefit decision-makers when making management decisions. In this study, we utilized weather forecast (WF) data combined with Sentinel-2 data to establish the deep-learning network and achieved an in-season county-scale wheat yield prediction in China’s main wheat-producing areas. We tested a combination of short-term WF data from the China Meteorological Administration to predict in-season yield at different forecast lengths. The results showed that explicitly incorporating WF data can improve the accuracy in crop yield predictions [Root Mean Square Error (RMSE) = 0.517 t/ha] compared to using only remote sensing data (RMSE = 0.624 t/ha). After comparing a series of WF data with different time series lengths, we found that adding 25 days of WF data can achieve the highest yield prediction accuracy. Specifically, the highest accuracy (RMSE = 0.496 t/ha) is achieved when predictions are made on Day of The Year (DOY) 215 (40 days before harvest). Our study established a deep-learning model which can be used for early yield prediction at the county level, and we have proved that weather forecast data can also be applied in data-driven deep-learning yield prediction tasks.

This paper proposes three feature extraction (FE) methods based on density estimation for hyperspectral images (HSIs). The methods are a mixture of factor analyzers (MFA), deep MFA (DMFA), and supervised MFA (SMFA). The MFA extends the Gaussian mixture model to allow a low-dimensionality representation of the Gaussians. DMFA is a deep version of MFA and consists of a two-layer MFA, i.e, samples from the posterior distribution at the first layer are input to an MFA model at the second layer. SMFA consists of single-layer MFA and exploits labeled information to extract features of HSI effectively. Based on these three FE methods, the paper also proposes a framework that automatically extracts the most important features for classification from an HSI. The overall accuracy of a classifier is used to automatically choose the optimal number of features and hence performs dimensionality reduction (DR) before HSI classification. The performance of MFA, DMFA, and SMFA FE methods are evaluated and compared to five different types of unsupervised and supervised FE methods by using four real HSIs datasets.

The timely and accurate prediction of winter wheat yields is of importance in maintaining food security. However, existing deep-learning methods used for crop yield prediction are limited. While most methods utilize recurrent neural networks (RNNs) to interpret crop time series data, they struggle to learn geographical spatial information from input data and often prove challenging to interpret with prior knowledge. In this study, hyperspectral images were used as the input to a BS-Nets network for band selection, and a graph-based RNN framework GT-long-short-term memory (LSTM) [two channels based LSTM-graph neural network (GNN)], was proposed for predicting the winter wheat yield at the county level. Using the BS-Nets for hyperspectral bands selection at the field scale, we obtained the top 4 bands in selection results for all six stages, the results were band 46 (791 nm), 50 (825 nm), 66 (954 nm), and 161 (2484 nm). Based on the results of hyperspectral bands selection, at the county scale, the similar wavelength bands of Sentinel-2 red-edge 3 (783 nm), NIR (834 nm), red-edge 4 (865 nm), SWIR2 (2190 nm) were chosen as inputs for the GT-LSTM county-level estimates of winter wheat yield. When only remote sensing data were used, the highest prediction accuracy ( $R^{2}= 0.688$ , RMSE = 0.54 t/ha) was obtained for DOY135 (30 days before harvest). The incorporation of the meteorological data improved the accuracy by 7% ( $R^{2}= 0.714$ , RMSE = 0.50 t/ha), and the optimal time for predicting wheat yield was at DOY115 (50 days before harvest). Further addition of GNN layers to the model improved the accuracy of the results by an additional 14% ( $R^{2}= 0.757$ , RMSE = 0.43 t/ha), and the best prediction results were then obtained at DOY105 (60 days before harvest).