Image Classification of Wheat Rust Based on Ensemble Learning.

Rust is a common disease in wheat that significantly impacts its growth and yield. Stem rust and leaf rust of wheat are difficult to distinguish, and manual detection is time-consuming. With the aim of improving this situation, this study proposes a method for identifying wheat rust based on ensemble learning (WR-EL). The WR-EL method extracts and integrates multiple convolutional neural network (CNN) models, namely VGG, ResNet 101, ResNet 152, DenseNet 169, and DenseNet 201, based on bagging, snapshot ensembling, and the stochastic gradient descent with warm restarts (SGDR) algorithm. The identification results of the WR-EL method were compared to those of five individual CNN models. The results show that the identification accuracy increases by 32%, 19%, 15%, 11%, and 8%. Additionally, we proposed the SGDR-S algorithm, which improved the f1 scores of healthy wheat, stem rust wheat and leaf rust wheat by 2%, 3% and 2% compared to the SGDR algorithm, respectively. This method can more accurately identify wheat rust disease and can be implemented as a timely prevention and control measure, which can not only prevent economic losses caused by the disease, but also improve the yield and quality of wheat.

Retrieving Sun-Induced Chlorophyll Fluorescence from Hyperspectral Data with TanSat Satellite.

A series of algorithms for satellite retrievals of sun-induced chlorophyll fluorescence (SIF) have been developed and applied to different sensors. However, research on SIF retrieval using hyperspectral data is performed in narrow spectral windows, assuming that SIF remains constant. In this paper, based on the singular vector decomposition (SVD) technique, we present an approach for retrieving SIF, which can be applied to remotely sensed data with ultra-high spectral resolution and in a broad spectral window without assuming that the SIF remains constant. The idea is to combine the first singular vector, the pivotal information of the non-fluorescence spectrum, with the low-frequency contribution of the atmosphere, plus a linear combination of the remaining singular vectors to express the non-fluorescence spectrum. Subject to instrument settings, the retrieval was performed within a spectral window of approximately 7 nm that contained only Fraunhofer lines. In our retrieval, hyperspectral data of the O2-A band from the first Chinese carbon dioxide observation satellite (TanSat) was used. The Bayesian Information Criterion (BIC) was introduced to self-adaptively determine the number of free parameters and reduce retrieval noise. SIF retrievals were compared with TanSat SIF and OCO-2 SIF. The results showed good consistency and rationality. A sensitivity analysis was also conducted to verify the performance of this approach. To summarize, the approach would provide more possibilities for retrieving SIF from hyperspectral data.

A Deep-Learning-Based Approach for Wheat Yellow Rust Disease Recognition from Unmanned Aerial Vehicle Images.

Yellow rust is a disease with a wide range that causes great damage to wheat. The traditional method of manually identifying wheat yellow rust is very inefficient. To improve this situation, this study proposed a deep-learning-based method for identifying wheat yellow rust from unmanned aerial vehicle (UAV) images. The method was based on the pyramid scene parsing network (PSPNet) semantic segmentation model to classify healthy wheat, yellow rust wheat, and bare soil in small-scale UAV images, and to investigate the spatial generalization of the model. In addition, it was proposed to use the high-accuracy classification results of traditional algorithms as weak samples for wheat yellow rust identification. The recognition accuracy of the PSPNet model in this study reached 98%. On this basis, this study used the trained semantic segmentation model to recognize another wheat field. The results showed that the method had certain generalization ability, and its accuracy reached 98%. In addition, the high-accuracy classification result of a support vector machine was used as a weak label by weak supervision, which better solved the labeling problem of large-size images, and the final recognition accuracy reached 94%. Therefore, the present study method facilitated timely control measures to reduce economic losses.

Local temperature responses to actual land cover changes present significant latitudinal variability and asymmetry.

Land cover changes (LCCs) affect surface temperatures at local scale through biophysical processes. However, previous observation-based studies mainly focused on the potential effects of virtual afforestation/deforestation using the space-for-time assumption, while the actual effects of all types of realistic LCCs are underexplored. Here, we adopted the space-and-time scheme and utilized extensive high-resolution (1-km) satellite observations to perform the first such assessment. We showed that, from 2006 to 2015, the average temperature in the areas with LCCs increased by 0.08 K globally, but varied significantly across latitudes, ranging from -0.05 to 0.18 K. Cropland expansions dominated summertime cooling effects in the northern mid-latitudes, whereas forest-related LCCs caused warming effects elsewhere. These effects accounted for up to 44.6% of overall concurrent warming, suggesting that LCC influences cannot be ignored. In addition, we revealed obvious asymmetries in the actual effects, i.e., LCCs with warming effects occurred more frequently, with stronger intensities, than LCCs with cooling effects. Even for the mutual changes between two covers in the same region, warming LCCs generally had larger magnitudes than their cooling counterparts due to asymmetric changes in transition fractions and driving variables. These novel findings, derived from the assessment of actual LCCs, provide more realistic implications for land management and climate adaptation policies.

Remote Sensing of Agro-droughts in Guangdong Province of China Using MODIS Satellite Data.

A practical approach was developed in the study for drought monitoring in Guangdong province of China on the basis of vegetation supply water index (VSWI) and precipitation distance index (PDI). A comprehensive index for assessment of agro-drought severity (SADI) was then established from the normalized VSWI and PDI. Using MODIS satellite images and precipitation data from ground-observed meteorological stations, we applied the approach to Guangdong for drought monitoring in 2006. The monitoring results showed that the drought severity on average was very low in the province during the main growing season from May to September in 2006. However, seasonal variation of the severity was also obvious in difference counties of the province. Higher severity of drought could be seen in the periods of late-June (In China each month is traditionally divided into 3 periods. Each is with 10 days and has different names. This division system is mainly with consideration of farming seasons hence has been widely used as the basis of drought monitoring periods in China. In order to keep this tradition, we define, for example, for June, the early-June as the period from 1st to 10th of June, the mid-June as the period from 11th to 20th, and the late-June as the period from 21st to 30th. So mid-August denotes the period from 11th to 20th of August, and early-July the period from 1st to 10th of July, and so on.), early-July, mid-August and late-September. Regionally, Leizhou Peninsula in the west had the most serious drought before mid-May. Validation indicated that our monitoring results were generally consistent with the drought statistics data and the results from Chinese National Satellite Meteorological Center (CNSMC), which used only remote sensing data. This consistence confirmed the applicability of our approach for drought monitoring. Our better identification of drought severity in Leizhou Peninsula of western Guangdong than that of CNSMC might suggest that the approach developed in the study was able to provide a better alternative to increase the accuracy of drought monitoring for agricultural administration and farming.