Search

Abstract Northwest China has undergone notable alterations in climate and vegetation growth in recent decades. Nevertheless, uncertainties persist concerning the response of different vegetation types to climate change and the underlying mechanisms. This study utilized the Normalized Difference Vegetation Index (NDVI) and three sets of meteorological data to investigate the interannual variations in the association between vegetation and climate (specifically precipitation and temperature) from 1982 to 2015. Several conclusions were drawn. (1) RNDVI-GP (relationship between Growing Season NDVI and precipitation) decreased significantly across all vegetation, while RNDVI-GT (relationship between Growing Season NDVI and temperature) showed an insignificant increase. (2) Trends of RNDVI-GP and RNDVI-GT exhibited great variations across various types of vegetation, with forests displaying notable downward trends in both indices. The grassland exhibited a declining trend in RNDVI-GP but an insignificant increase in RNDVI-GT, while no significant temporal changes in RNDVI-GP or RNDVI-GT were observed in the barren land. (3) The fluctuations in RNDVI-GP and RNDVI-GT closely aligned with variations in drought conditions. Specifically, in regions characterized by VPD (vapor pressure deficit) trends less than 0.02 hpa/yr, which are predominantly grasslands, a rise in SWV (soil water volume) tended to cause a reduction in RNDVI-GP but an increase in RNDVI-GT. However, a more negative trend in SWV was associated with a more negative trend in both RNDVI-GP and RNDVI-GT when the VPD trend exceeded 0.02 hPa/yr, primarily in forests. Our results underscore the variability in the relationship between climate change and vegetation across different vegetation types, as well as the role of drought in modulating these associations.

In the past, the use of remote sensing for winter wheat growth monitoring mainly relied on the relative growth assessment of a single vegetation index, such as normalized Vegetation index (NDVI). This study advanced the methodology by integrating field-measured data with Sentinel-2 data. In addition to NDVI, it innovatively incorporated two parameters, aboveground biomass (AGB) and leaf area index (LAI), for a more comprehensive relative growth assessment. Furthermore, the study employed the agricultural production systems simulator (APSIM) model to use LAI and AGB for absolute growth monitoring. The results showed that the simulated LAI and AGB closely match the field-measured values throughout the entire growth period of winter wheat under various conditions (R2 > 0.9). For relative growth monitoring, NDVI showed significant linear positive correlations (r > 0.74 and P< 0.05) with both LAI and AGB simulated by the APSIM model. Overall, this research shows that LAI and AGB obtained from the APSIM model provide a more detailed and accurate approach to monitoring of winter wheat growth. This improved monitoring capability can support effective land management arable and provide technical guidance to advance precision agriculture practices.

Lossless remote sensing image compression aims to reduce the storage size of images without any information loss, ensuring that the decompressed image is identical to the original one. Most existing methods focus on lossy image compression that reduce the storage cost with certain data loss. It is challenging to perform lossless compression due to the very high-resolution images, long encoding–decoding time, and low compression efficiency. In this article, we propose a lossless compression framework that compresses remote sensing images in a coarse-to-fine manner. Specifically, checkerboard segmentation is applied on each image to generate six subimages from the main diagonal and counter-diagonal of each channel to maximally preserve the detail and structural information. The subimages from the main diagonal are initially compressed by a traditional compression method, while the subimages from the counter-diagonal are compressed channel by channel using our proposed probability prediction network (P2Net) and arithmetic coding with the previously encoded subimages from both the main diagonal and counter-diagonal as prior knowledge. The proposed P2Net consists of a upsampling module, a feature enhancement module, a downsampling module, and a probability prediction module to learn the discrete probability distribution of pixels. Lossless compression is conducted with arithmetic coding on the discrete probability distribution. To the best of our knowledge, this is the first deep learning-based lossless compression framework for three-channel remote sensing images. Experiments demonstrate that our framework outperforms the state-of-the-art methods and requires about 3.4 s to compress a 1024 $\times \, \text{1024}\,\times$ 3 image with 2.9% efficiency improvement compared to JPEG XL.

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 study presents a command filtered control scheme for multi-input multi-output (MIMO) strict feedback nonlinear unmodeled dynamical systems with its applications to power systems. To deal with dynamic uncertainties, a dynamic signal is introduced, together with radial basis function neural networks (RBFNNs) to overcome the influences of the dynamic uncertainties. Command filters (CFs) are used to prevent the explosion of complexity, where the compensating signals can eliminate the effect of filter errors. Compared with single-input single-output strict feedback nonlinear systems, the method proposed in this study has more suitability. In the end, the simulation experiments are carried out by applying the developed algorithm to power systems, where the simulation results verify the efficacy of the approach proposed.

To conduct precision geometric correction of Landsat-8 data, all ground control points from the Global Land Survey (GLS) 2005 are typically selected, thereby making the process time consuming and labor intensive. This paper developed an optimal selection algorithm for choosing representative points. The optimal technique consists of three steps, including 1) evaluating the spatial distribution patterns of points from GLS2005, 2) extracting ideal points positions from each scene based on the spatial distribution patterns obtained in the first step, and 3) selecting real representatives GCPs from the original large number of GCPs based on the positions of ideal points. One hundred individual Landsat-8 images were chosen for precision geometric correction to assess the robustness and efficiency of the method. Experimental result demonstrated that the approach could only consume 1/10 processing time or less when compared to that using the full set of original GCPs while still achieving comparable geometric accuracy. The developed technique will make an important contribution to improving the efficiency of precision geometric product generation systems for Landsat-8 images. [ABSTRACT FROM AUTHOR]