Search

Abstract The currently used standardised precipitation index (SPI) does not allow for a reliable assessment of the impact of drought due to the small and unevenly distributed network of meteorological stations. Hopes for developing methods to assess the impact of droughts are pinned on remote data acquisition and the use of analysis of aerial photographs and satellite scenes. The aim of this study is to assess the occurrence of drought based on the normalised difference vegetation index (NDVI) and SPI at multiple time scales (1-, 3-, and 6-, 9- and 12-month). NDVI values do not simply reflect meteorological drought. However, the spatial co-occurrence of meteorological drought with drought defined on the basis of the NDVI index was demonstrated. The study presents a new approach to identifying drought characterized by SPI and NDVI based on the bivariate choropleth map method, which can indicate the actual places of drought occurrence. The study was carried out for the upper Noteć catchment located in Central Poland.

Post-mined reclamation is an essential phase in coal mining operations, ensuring that the ex-mining area can function again according to its intended purpose in the future. This study aimed to elucidate the differences in planting years of post-mined reclamation at a coal mine in the Paringin area, South Kalimantan, Indonesia, and compared them to undisturbed areas for the years 2003 and 2023. NDVI was used for land cover analysis based on the Ministry of Energy and Mineral Resource Regulation, and the ultimate criterion for 100% success in post-mined reclamation is vegetation canopy coverage. The NDVI results showed an improvement in NDVI values for the post-mined reclamation area from 2003 to 2023, indicating an improvement in land cover due to the revegetation process. In 2023, the NDVI results of the post-mined reclamation for eight and twenty years of tree planting showed NDVI values of 0.6-0.7 (moderate vegetation). However, the results of field observations of the twenty-year post-mined reclamation tree condition indicate the non-survival of fast-growing tree species, such as Albizia chinensis. The composition of fast-growing and local tree species, with a minimum proportion of 60:40, and systematic tree distribution across the post-mined reclamation area are required to maintain canopy coverage of the post-mined reclamation area in the long term. Fast-growing tree species, as pioneers, have short to medium life periods. Therefore, the ultimate criterion for 100% success in post-mined reclamation for canopy coverage should be based on local tree species, serving as the basis for releasing the reclamation bond.

Abstract Background The time‐series data of the Normalized Difference Vegetation Index (NDVI) is a crucial indicator for global and regional vegetation monitoring. However, the current assessment of global and regional long‐term vegetation changes is subject to large uncertainties due to the lack of spatiotemporally continuous time‐series data sets. Methods In this study, a long time‐series monthly NDVI data set with a spatial resolution of 250 m from 1982 to 2020 was developed by combining Moderate Resolution Imaging Spectroradiometer (MODIS) and AVHRR (Advanced Very High‐Resolution Radiometer) time‐series NDVI products using the Random Forest (RF) downscaling model. Results Compared to the MODIS NDVI product, the fused product shows RMSE and mean absolute error ranging from 0 to 0.075 and from 0 to 0.05, respectively, with R2 values mostly above 0.7. Conclusions The long time‐series NDVI products generated in this study are reliable in terms of accuracy and have great potential for long‐term dynamic monitoring of terrestrial ecosystems on the Qinghai–Tibet Plateau.

Abstract This study assesses the relationships between vegetation dynamics and climatic variations in Pakistan from 2000 to 2023. Employing high-resolution Landsat data for Normalized Difference Vegetation Index (NDVI) assessments, integrated with climate variables from CHIRPS and ERA5 datasets, our approach leverages Google Earth Engine (GEE) for efficient processing. It combines statistical methodologies, including linear regression, Mann–Kendall trend tests, Sen's slope estimator, partial correlation, and cross wavelet transform analyses. The findings highlight significant spatial and temporal variations in NDVI, with an annual increase averaging 0.00197 per year (p

This study aims to develop a plant health monitoring system suitable for vertical farms. It began by creating a multispectral LED with UVA and NIR light sources and an IoT device capable of controlling the LED spectrum. The IoT device integrates a camera with switchable filters and RGB CMOS sensor to simultaneously calculate SI-NDVI (single-image normalized difference vegetation index) and UV-NDVI (UV induce red chlorophyll fluorescence normalized difference vegetation index).A lettuce cultivation experiment was conducted on a planting shelf in a controlled environmental room, with two cultivation planters containing the same nutrient solution and red lettuce variety. SI-NDVI and UV-NDVI were calculated every three hours to compare differences. Results showed that both UV-NDVI and SI-NDVI trends were similar in monitoring lettuce growth. However, UV-NDVI was more sensitive to plant health than SI-NDVI. By inducing drought stress, the UV-NDVI indicator was able to detect water deficiency anomalies earlier than visual observation.

Woody vegetation restoration projects are an important feature of landscape function in Indonesian karst savannas. Understanding the relationship between available moisture and vegetation condition can assist with the planning and implementation of revegetation efforts. Working at vegetation restoration sites in East Nusa Tenggara, Indonesia, we applied a windowed cross-correlation method to mean values of NDVI to examine the lag between moisture input and NDVI response for both rainfall and soil moisture between 1999 and 2018. To test for increasing or decreasing trends in NDVI and rainfall time series, we undertook Mann–Kendall trend analyses. We identified increasing trends in Landsat 7 NDVI at two of four restoration sites, with annual increases in NDVI of 2.7 and 3.74 × 10−4 respectively. We found that rainfall dependent sites had significant Pearson’s correlations with NDVI ranging from 0.52 to 0.71, while NDVI was not correlated with rainfall at shallow groundwater sites. There was a clear negative effect of the very dry period on all sites, and this was less pronounced at shallow groundwater sites. Wet years resulted in a positive response to NDVI across all sites, while the response was lower in very wet years with annual rainfall above 1,200 mm. We found that between 2 and 4 months of antecedent rainfall gave the highest correlation with NDVI, while for soil moisture the closest relationship was found with no lag and 1 month lag. Through this study, we demonstrated the applicability of using NDVI, rainfall, and soil moisture trend analyses to identify groundwater-dependent vegetation patches and monitor the effectiveness of vegetation restoration.

ABSTRACTSpatial-temporal dynamics monitoring of Arctic vegetation structure (i.e. distribution range of tundra and forest) is of great significance for evaluating global warming effect. Currently, time-series monitoring of Arctic vegetation structure relies primarily on the Normalized Difference Vegetation Index (NDVI), which is derived from optical remote sensing images. However, because of factors such as the long revisit period of satellites and the impact of climate, optical observations are severely lacking in the Arctic region. This results in NDVI time-series data highly discontinuous and difficult to reflect actual variations in Arctic vegetation structure, and the traditional time-series reconstruction method would usually fail for severe missing conditions. Therefore, this study developed a Time Series Reconstruction method considering Periodic Trend (TSR-PT), which is specifically for alleviating the severe missing observation condition in the Arctic region. It can separate the phenological change and trend change of the incomplete time series NDVI, and borrow the information from the neighboring unchanged years for compensate of the missing observations in current years, based on the learned inter-annual and intra-annual correlation. We explore its usability in monitoring vegetation structure variation in Vorkuta region (transition zone of tundra and taiga in the Arctic Circle) based on MODIS data. It is found that the proposed TSR-PT is able to reconstruct NDVI with reasonable phenological feature even the missing rate reaches over 70%, which is usually falsely constructed by traditional filtering or fitting method, and suppress them by 0.038 in terms of RMSE; besides, we find that since 21-century, the Arctic trees have continued to increase and encroach the original tundra ecosystem, which caused a largely Arctic vegetation structural change, and we believe the proposed method would largely promote the Arctic vegetation research.

The use of sensors for variable rate nitrogen (VRN) applications is transitioning from equipment-based to drone and satellite technologies. However, regional algorithms, initially designed for proximal active sensors, require evaluation for compatibility with remotely sensed reflectance and N-rate predictions. This study observed normalized difference vegetation index (NDVI) data from six small grain and two corn fields over three years. We employed three platforms: tractor-mounted active sensors (T-NDVI), passive multispectral drone (D-NDVI), and satellite (S-NDVI) sensors. Averaged NDVI values were extracted from the as-applied equipment polygons. Correlations between NDVI values from the three platforms were positive and strong, with D-NDVI consistently recording the highest values, particularly in areas with lower plant biomass. This was attributed to D-NDVI's lower soil reflectance and its ability to measure the entire biomass within equipment polygons. For small grains, sensors spaced on equipment booms might not capture accurate biomass in poor-growing and low NDVI regions. Regarding VRN, S-NDVI and D-NDVI occasionally aligned with T-NDVI recommendations but often suggested half the active sensor rate. Final yields showed some correlation with landscape variables, irrespective of N application. This finding suggests the potential use of drone or satellite imagery to provide multiple NDVI maps before application, incorporating expected landscape responses and thereby enhancing VRN effectiveness.

Investigating the long-term dynamics in the canopy proves to be difficult due to the short observational records of the normalized difference vegetation index (NDVI). To explore the linkage between tree growth, NDVI dynamics and large-scale atmospheric circulation in the Greater Khingan Mountain, Northeast China, we established a chronology of Larix gmelinii tree ring width at three elevations (870–920 m, 1,100–1,150 m and 1,270–1,320 m) in the northern foothills of the mountain range. We then calculated the correlations between the tree ring chronologies and NDVI and climate factors, and reconstructed the NDVI time series from June to September 1759–2021 in the region based on the middle-elevation tree ring chronology. The results identify the positive effect of temperature (r = 0.56, p < 0.01) and the negative effect of precipitation (r = −0.44, p < 0.01) in the growing season as the main influencing factors of NDVI for the study period (1981–2019). The 11-year moving average of the reconstructed NDVI series reveals two periods of high canopy vigor (1898–1926 and 2009–2013) and three periods of low canopy vigor (1860–1962, 1882–1888 and 1968–1977) in the last 263 years. These periods correspond to drought events recorded in the historical literature. Wavelet analysis shows that the reconstructed sequences exhibited 11–13, 23–25, and 39–42 years period variations. Integrating this with spatial correlation analysis reveals that tree growth in the Mangui region was impacted by the combined effect of the North Pacific Decadal Oscillation and the North Atlantic Multidecadal Oscillation. The results of this paper provide a reference for the study of vegetation change patterns in the northern foothills of the Greater Khingan Mountains.

Droughts are one of the most catastrophic natural disasters on the planet, impacting millions of people in various ways (e.g., food security, economic losses, and migration). The growing severity of droughts and their catastrophic effects on society in India's semi-arid regions necessitate better drought monitoring and assessment systems. Traditional mathematical methods like Standardized Precipitation Index (SPI), Palmer Drought Severity Index (PDSI), and Climate Moisture Index (CMI), etc., are used to analyze drought intensity. In the present study, analysis of historical rainfall data from the Parbhani district (2000–2020) was conducted to identify patterns in normal, actual, and % deviation of actual rainfall from normal for two contrasting years (2020: +4.1 % deviation, 2015: −53.73 % deficit), with a focus on drought analysis using dry spell data from the Government senses. The satellite images for the years 2015 and 2020 were gathered at 16-day intervals, and remote sensing techniques were employed to calculate NDDI (normalized difference drought index) using NDVI (normalized difference vegetation index) and NDWI (normalized difference water index). The comparative analysis of NDVI and NDWI interpreted greater value during normal rainy conditions in 2020, whereas it was low in 2015 due to less rainfall and higher dry spells. NDDI reflects positively; it was observed that the mean area under the Mild drought class in 2015 (90.9 %) was higher than in 2020 (84.9 %). Variable rainfall distribution and dry spell patterns caused severe drought in 2015, according to vegetation indices. The study utilized remote sensing to investigate drought and corroborated its findings with India Meteorological Department (IMD) rainfall and dry spell data. VIs can therefore be utilized as an independent indicator that complements conventional techniques.

Long-term, reliable datasets of satellite-based vegetation condition are essential for understanding terrestrial ecosystem responses to global environmental change, particularly in Australia, which is characterised by diverse ecosystems and strong interannual climate variability. We comprehensively evaluate several existing global Advanced Very High Resolution Radiometer (AVHRR) normalised-difference vegetation index (NDVI) products for their suitability for long-term vegetation monitoring in Australia. Comparisons with the MODIS NDVI highlight significant deficiencies, particularly over densely vegetated regions. Moreover, all the assessed products failed to adequately reproduce the interannual variability in the pre-MODIS era as indicated by Landsat NDVI anomalies. To address these limitations, we propose a new approach to calibrating and harmonising NOAA's Climate Data Record of AVHRR NDVI to the MODIS MCD43A4 NDVI for Australia using a gradient-boosting decision tree ensemble method. Two versions of the datasets are developed, one incorporating climate data in the predictors (“AusENDVI-clim”: Australian Empirical NDVI-climate) and another that is independent of climate data (“AusENDVI-noclim”). These datasets, spanning 1982–2013 at a spatial resolution of 0.05° and with a monthly time step, exhibit strong correlations (r2=0.89–0.94) and low mean errors compared with MODIS MCD43A4 NDVI (mean absolute error (MAE) = 0.014–0.028, RMSE = 0.021–0.046), accurately reproducing seasonal cycles over densely vegetated regions. Furthermore, they closely replicate the interannual variability in vegetation condition in the pre-MODIS era. A reliable method for gap-filling the AusENDVI record is also developed that leverages climate, atmospheric CO2 concentration, and woody-cover fraction predictors. The resulting synthetic NDVI dataset shows excellent agreement with the MODIS MCD43A4 NDVI and the recalibrated AVHRR NDVI time series (r2=0.82–0.95, MAE = 0.016–0.029, RMSE = 0.039–0.041). Finally, we provide a complete 41-year dataset where the gap-filled AusENDVI-clim from January 1982 to February 2000 is joined with the MODIS MCD43A4 NDVI from March 2000 to December 2022. Analysing 40-year per-pixel trends in Australia's annual maximum NDVI revealed increasing values, and shifts in the timing, of the annual peak NDVI across most of the continent, underscoring the dataset's potential to address crucial questions regarding the changing vegetation phenology and its drivers. The AusENDVI dataset can be used for studying Australia's changing vegetation dynamics and downstream impacts on the terrestrial carbon and water cycles, and it provides a reliable foundation for further research into the drivers of vegetation change. AusENDVI is open access and available at https://doi.org/10.5281/zenodo.10802703 (Burton et al., 2024).

This paper presents an actuator fault-tolerant control (FTC) strategy for a hexacopter unmanned aerial vehicle (UAV) designed specifically for precision agriculture applications. The proposed approach integrates advanced sensing techniques, including the estimation of Near-Infrared (NIR) reflectance from RGB imagery using the Pix2Pix deep learning network based on conditional Generative Adversarial Networks (cGANs), to enable the calculation of the Normalized Difference Vegetation Index (NDVI) for health assessment. Additionally, trajectory flight planning is developed to ensure the efficient coverage of the targeted agricultural area while considering the vehicle’s dynamics and fault-tolerant capabilities, even in the case of total actuator failures. The effectiveness of the proposed system is validated through simulations and real-world experiments, demonstrating its potential for reliable and accurate data collection in precision agriculture. An NDVI test was conducted on a sugarcane crop using the estimated NIR to assess the crop’s condition during its tillering stage. Therefore, the main contributions this paper include (i) the development of an actuator FTC strategy for a hexacopter UAV in precision agriculture applications, integrating advanced sensing techniques such as NIR reflectance estimation using deep learning network; (ii) the design of a flight trajectory planning method ensuring the efficient coverage of the targeted agricultural area, considering the vehicle’s dynamics and fault-tolerant capabilities; (iii) the validation of the proposed system through simulations and real-world experiments; and (iv) the successful integration of FTC scheme, advanced sensing, and flight trajectory planning for reliable and accurate data collection in precision agriculture.

The incompleteness of the normalized difference vegetation index (NDVI) time series (TS) restricts its expanded applications in key domains. Although spatio-temporal hybrid methods show promise in TS reconstruction, reliance on auxiliary data in most existing approaches introduces errors and increases workload. Furthermore, NDVI values marked as contaminated in the quality assessment (QA) data are underutilized. Ultimately, when utilizing spatial information, most methods are ineffective for the representation of land-use changes. Considering these issues, we propose a local peak Savitzky–Golay (LPSG) method for spatio-temporal reconstruction of Landsat NDVI TS. First, we construct a local peak neighborhood weighted interpolation (LPNWI) method that fully utilizes all original values to fill gaps. Second, we design a slope change decision tree (SC-DT) method for identifying residual noise, thereby mitigating the impact of QA errors on reconstruction results. Third, multidimensional calibration with weighted spatial reference (MDC-WSR) method is proposed to enhance utilization of spatial information by improving traditional correlation coefficient calculations and generating a multiyear spatial reference, which effectively reflects land-use changes. Experiments on Landsat NDVI TS data in the Qinghai–Tibet Plateau (2013–2022) show that: 1) LPSG outperforms other methods in mitigating the impact of QA errors, preserving TS peaks and details, and maintaining spatial continuity; 2) LPSG exhibits superior performance, with average RMSE reductions ranging from 0.00018 to 0.00750 compared to other methods under both correct and incorrect QA; and 3) LPSG demonstrates good robustness under various gap conditions and effectively restores TS of pixels affected by land-use changes.

Multispectral reflectance—signals reflected from the Earth's surface across different wavelengths—is a primary data source for most remote sensing applications. However, obtaining complete cloud-free multispectral reflectance time series during the vegetation growing season remains challenging due to cloud contamination and limitations of existing reconstruction methods. To address the challenge, this study proposed a novel normalized difference vegetation index (NDVI)-guided bi-directional recurrent reconstruction model for multispectral reflectance time series (referred to as “NB-Re3”), which aimed to reconstruct dense time series of reflectance images by exploiting the dependence of NDVI on multispectral reflectance. NB-Re3 utilizes a temporal convolutional network to capture the temporal trends in the NDVI data and a bidirectional long short-term memory to integrate the temporal features of the NDVI with the cloud-free reflectance data. The architecture establishes a robust dynamic NDVI-reflectance relationship while capturing temporal dependencies and multispectral autocorrelations of multiple spectral bands. We compared the performance of NB-Re3 with four representative methods (MNSPI, HANTS, STAIR, and U-TILSE) in reconstructing multispectral reflectance time series, ranging from the visible bands to near-infrared and short-wave infrared bands, at two challenging sites: the irrigated area of Colleambally, Australia, and the cultivated area of Rikaze on the Southern Tibetan Plateau, China. The result showed that NB-Re3 kept superiority with the lowest root-mean-square error values and highest correlation coefficients values. The effectiveness of integrating high-quality NDVI time series and using multispectral autocorrelation to improve reflectance time-series reconstruction was further confirmed by the ablation experiments. It is concluded that NB-Re3 shows promise for generating long-term cloud-free reflectance time-series products tailored for ecological and agricultural applications.

Ensuring sustainable and profitable agriculture is critical for addressing global food security challenges. This has resulted in the need for automation in plant health identification. However, this objective is hampered by the lack of efficient image-processing methods and the need for extensive datasets for training deep learning models for plant disease diagnosis. To overcome the need for extensive training data, the proposed Localized Normalized Difference Vegetation Index (LNDVI) uses zero-shot plant detection models such as Grounded Dino and state-of-the-art methods for image segmentation such as Segment Anything Model (SAM) are leveraged. This also expands the capabilities of the system to diagnose plant health beyond known plant species available as part of training set. The proposed system uses synthetic Normalized Difference Vegetation Index (NDVI) to estimate the chlorophyll content of the plant through RGB images alone instead of using the combination of RGB and near Infra-red (nIR) bands used in contemporary works. Since NDVI value is greatly affected by the amount of light present while the image is captured, we also present an irradiation estimation metric that uses CIE XYZ (Tristimulus values), Hue, Saturation and Value (HSV) and CIE LAB color spaces as well as correlated color temperatures, which automatically normalizes the NDVI threshold for health classification of the image, enabling a more precise analysis of plant health. Using the Grounding Dino provided an accuracy of 99.994% in terms of detecting plants from the phenotyping dataset. The segmentation of plant region in images is reported using Intersection over Union (IoU). While using the Segment Anything Model (SAM), an average accuracy of 95.884% was obtained for clustered plants while the average accuracy was even better at 97.031% for individual plants. Significant differences were observed for plant health classification while using Localized Normalized Difference Vegetation Index (LNDVI) approach when compared to NDVI.

Remote sensing plays a vital role in analyzing urban changes. In this regard, various datasets collected from satellites today serve as a foundation for decision-makers and urban planners. This study compares the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Built-up Index (NDBI) as indicators for the creation of surface heat islands. Using Landsat 8 OLI/TIRS C2 L2 images, spatial correlations between land surface temperature (LST) were examined for August 2013, 2019 and 2023. Urban heat islands (UHI) are a contemporary phenomenon and increasingly common in large urban areas compared to surrounding, less populated areas. With the advancement in remote sensing, it is possible to adequately determine the spatial differentiation and prevalence of urban heat islands (UHI). The study is based on Landsat 8 satellite image sets for the Sarajevo basin in August 2013, 2019 and 2023, which were used to analyze LST, NDVI, and NDBI indices. This work indicates a relationship between LST and NDVI but varies depending on the analyzed year. Normalized Difference Built-up Index (NDBI) serves as a suitable indicator for surface UHI effects and can be used as an indicator to assess its spatial distribution within a larger urban environment.

Monitoring vegetation dynamics is essential for ecological processes, environmental changes, and natural resource protection. Fine-scale representation of vegetation indices is necessary for regions with complex topography and high diversity species. However, the advanced very-high-resolution radiometer (AVHRR), which covers an extensive time range with high temporal resolution, does not provide normalized difference vegetation index (NDVI) data with sufficient spatial resolutions for a detailed analysis of vegetation changes. The moderate resolution imaging spectroradiometer (MODIS), which has a higher temporal and spatial resolution, has only been limited to the last few decades. To deal with these issues, we propose a multiscale residual convolutional neural network (MRCNN) that utilizes a multiscale structure with a residual convolutional neural network to combine MODIS NDVI and AVHRR NDVI data. The MRCNN algorithm improved mean absolute error (MAE) and root mean squared error (RMSE) by 0.026 and 0.032, respectively, resulting in a 64.38% improvement for MAE and 62.79% improvement for RMSE compared to AVHRR NDVI. It also increased the peak signal-to-noise ratio by 28.5% and the structural similarity index by 16.2%. The MRCNN method accurately captures the actual state of MODIS NDVI and consistently tracks changing trends in the vegetation index. It is exact in complex terrain and diverse vegetation areas. This method enhances the spatial resolution of AVHRR NDVI and significantly improves the accuracy of monitoring nationwide vegetation index changes over 30 years. The findings establish a solid scientific foundation for implementing ecological conservation measures and promoting sustainable vegetation growth.

ABSTRACTEnvironmental changes are significantly modifying terrestrial vegetation dynamics, with serious consequences on Earth system functioning and provision of ecosystem services. Land conditions are an essential element underpinning global sustainability frameworks, such as the Sustainable Development Goals (SDGs), requiring effective solutions to assess the impacts of changing land conditions induced by various driving forces. At the global scale, long-term increase of vegetation greening has been widely reported notably in seasonally snow-covered ecosystems as a response to warming climate. However, greening trends at the national scale have received less attention, although countries like Switzerland are prone to important changing climate conditions. Hereby, we used a 35-year satellite-derived annual and seasonal time-series of Normalized Difference Vegetation Index (NDVI) to assess vegetation greenness evolution at different spatial and temporal scales across Switzerland and related them to temperature, precipitation, and land cover to investigate possible responses of changing climatic conditions. Results indicate that there is a statistically significant greening trend at the national scale with an NDVI mean increasing slope of 0.6%/year for the 61% significant pixels across Switzerland. In particular, the seasonal mean NDVI shows an important break for winter, autumn and spring seasons starting from 2010, potentially indicating a critical point of changing land conditions. At biogeographical scale, we observed an apparent clustering (Jura-Plateau; Northern-Southern Alps; Eastern-Western Alps) related to landscape characteristics, while forested land cover classes are more responsive to NDVI changes. Finally, the NDVI values are mostly a function of temperature at elevations below the tree line rather than precipitation. The findings suggest that multi-annual and seasonal NDVI can be a valuable indicator to monitor vegetation conditions at different scales and can provide complementary observations for national statistics on the ecological state of vegetation to monitor land affected by changing environmental conditions. This work is aiming at strengthening the insights into the driving factors of vegetation change and supporting monitoring changing land conditions to provide guidance for effective and efficient environmental management and sustainable development policy advice at the national scale.

Accurate prediction of vegetation indices is useful for helping maintain vegetation stability, sustaining food production, and reducing socioeconomic losses. The traditional convolutional long short-term memory (ConvLSTM) model for vegetation prediction ignores the spatial aggregation characteristics of the normalized difference vegetation index (NDVI) itself and the global dependence information in space. In this study, we propose a new NDVI prediction method, namely, the ConvLSTM with spatial autocorrelation and nonlocal attention module (ConvLSTM-SAC-NL), by combining the nonlocal attention module to capture long-range dependence and the spatial autocorrelation modeling based on the local Moran index to learn spatial dependence. The experimental results indicate that the ConvLSTM-SAC-NL model outperforms seven baseline forecasting models, with an R${}^{2}$ of 0.881 in monthly NDVI prediction in the Huangpi district of Wuhan city, relative to the R${}^{2}$ values of 0.758, 0.777, 0.741, 0.776, 0.804, 0.829, and 0.815 for random forest, support vector machine regression, long short-term memory, bidirectional long short-term memory, graph convolutional network, predictive recurrent neural network, and ConvLSTM models, respectively. Spatially, the prediction results of the ConvLSTM-SAC-NL model demonstrate improved accuracy over 91.49$\%$ of the study area when compared with ConvLTSM. Therefore, the proposed ConvLSTM-SAC-NL model could serve as an effective approach for short-term prediction of vegetation conditions at regional scales.