Landscape Drivers of Trail Formation in Peri-Urban Mountains: Insights from an Explainable Machine Learning Approach

A Bayesian network simulates the responses of soil organic carbon to environmental factors at a catchment scale

The main goals of this study are the object-based land-cover classification of LANDSAT-8 satellite imagery of 2014 and 2015, the quantitative assessment of gross and net changes of agricultural land, built-up areas, forest, bare soil and forest between 2014 and 2015, the quantification of the Normalized Difference Vegetation Index (NDVI) rates within these land-cover classes, and the change detection analysis between the NDVIs. The achieved overall accuracies of object-based classification for the 2014 and the 2015 land-cover maps were 82 and 87 %, respectively. Therefore, the achieved accuracies were considered to be acceptable for quantified change detection analyses. For the gross areas of agricultural land, forest and built-up areas an increase was observed. The agricultural gross area was 30,911 km2 in 2014 and 31,999 km2 in 2015. The gross area of the built-up land increased from 12,550 to 13,548 km2. The gross area of forest land changed from 8211 to 9175 km2. A decrease was observed in the gross area of grassland from 28,229 to 24,925 km2. This was primarily related to the land-cover shifts driven by agricultural activities. The gross areas of bare soil and water bodies did not change significantly. The net change analysis, however, revealed significant differences in comparison to gross change areas for both gains and losses of the land-cover classes. The net change analysis revealed positive net changes of 7229, 5576, 1337, 399, 951 km2 for agricultural land, forest, built-up areas, bare soil and water bodies, correspondingly. A negative net change of 2198 km2 was observed for grassland. This allows to conclude that the negative net change of grassland was related with the significant changes of grassland into agricultural land. No significant net changes were observed for the bare soil land-cover class. The classification of NDVIs derived from 2014 to 2015 LANDSAT-8 OLI satellite images showed that the vegetation cover of agricultural and built-up land-cover increased for the low (0.1–0.2) and medium (0.2–0.3) and decreased for the high NDVI values (0.3–1). The area of high (0.3–1) NDVIs in the forest land-cover was observed to be higher in 2015 than in 2014. A reduction in the low (0.1–0.2), medium (0.2–0.3) and high NDVI values (0.3–1) was observed for the grasslands land-cover. The reductions of the high NDVI rates (0.3–1) observed for agricultural, build-up and grasslands land-cover types may be related to agricultural and industrial activities and also to climate change impacts. For the entire coverage of Azerbaijan, positive and negative NDVI changes of 3170 and 3859 km2 respectively were observed.

ABSTRACTUnderstanding how species respond to environmental conditions can assist with conservation strategies and harvest management, especially in arctic and boreal regions that are experiencing rapid climate change. Although climatic influences on species distributions have been studied, broad‐scale effects of climate on survival are less well known. We examined the interactive effects of meteorological and remotely sensed environmental variables on survival of Dall's sheep (Ovis dalli dalli) lambs and adults by synthesizing radio‐telemetry data across their range. We used data from 9 studies of adult sheep and 2 studies of lambs that were conducted between 1997 and 2012 at sites spanning the species' range in Alaska, USA, and northwestern Canada. We obtained environmental variables throughout the range of Dall's sheep, including the normalized difference vegetation index (NDVI) from optical remote sensing, freeze‐thaw frequency (FTF) from passive microwave remote sensing, and gridded climate variables such as snow water equivalent, temperature, and precipitation. We used Cox proportional hazard regression to investigate the effects of environmental variables recorded during summer, winter, and the previous winter on annual survival rates of Dall's sheep lambs and adults. Summer NDVI was the most influential environmental factor affecting lamb survival, with improved lamb survival occurring in years with a high maximum NDVI. Also, lamb predation by coyotes (Canis latrans) and golden eagles (Aquila chrysaetos) decreased substantially with increasing NDVI. The previous winter FTF had the strongest effect on adult survival, with decreased survival occurring after winters with high FTF. In addition, these remotely sensed environmental factors interacted with meteorological factors to affect survival, such that effects of winter temperature depended on summer NDVI and winter FTF. Warm winters increased lamb survival only when preceded by summers with high NDVI, and warm winters increased adult survival only when winter FTF was low. Thus, potential benefits of climate warming may be counteracted if wintertime freeze‐thaw events markedly increase. Correlations among environmental variables across sites were low, and regional climate cycles such as the Pacific Decadal Oscillation (PDO) had weak effects, indicating substantial local variability in climatic conditions experienced by Dall's sheep across their range. These findings can help managers anticipate how Dall's sheep populations will respond to changes in local environmental conditions. Our results also highlight the utility of multiple remotely sensed environmental conditions for ungulate management, especially passive microwave products that provide valuable information on winter icing events. © 2020 The Wildlife Society.

The normalized difference vegetation index (NDVI) is a simple but powerful indicator, that can be used to observe green live vegetation efficiently. Since its introduction in the 1970s, NDVI has been used widely for land management, food security, and physical models. For these applications, acquiring NDVI in both high spatial resolution and high temporal resolution is preferable. However, there is generally a trade-off between temporal and spatial resolution when using satellite images. To relieve this problem, a convolutional neural network (CNN) based downscaling model was proposed in this research. This model is capable of estimating 10-m high resolution NDVI from MODIS (Moderate Resolution Imaging Spectroradiometer) 250-m resolution NDVI by using Sentinel-1 10-m resolution synthetic aperture radar (SAR) data. First, this downscaling model was trained to estimate Sentinel-2 10-m resolution NDVI from a combination of upscaled 250-m resolution Sentinel-2 NDVI and 10-m resolution Sentinel-1 SAR data, by using data acquired in 2019 in the target area. Then, the generality of this model was validated by applying it to test data acquired in 2020, with the result that the model predicted the NDVI with reasonable accuracy (MAE = 0.090, ρ = 0.734 on average). Next, 250-m NDVI from MODIS data was used as input to confirm this model under conditions replicating an actual application case. Although there were mismatch in the original MODIS and Sentinel-2 NDVI data, the model predicted NDVI with acceptable accuracy (MAE = 0.108, ρ = 0.650 on average). Finally, this model was applied to predict high spatial resolution NDVI using MODIS and Sentinel-1 data acquired in target area from 1 January 2020~31 December 2020. In this experiment, double cropping of cabbage, which was not observable at the original MODIS resolution, was observed by enhanced temporal resolution of high spatial resolution NDVI images (approximately ×2.5). The proposed method enables the production of 10-m resolution NDVI data with acceptable accuracy when cloudless MODIS NDVI and Sentinel-1 SAR data is available, and can enhance the temporal resolution of high resolution 10-m NDVI data.

ABSTRACTHigh-latitude systems in northwestern Canada and Alaska have warmed rapidly. The aim of this study was to examine how a remotely sensed proxy of vegetation productivity varied among mountain ranges with respect to elevation and climate from 2002–2017. Our study area included high-latitude mountains in Alaska, USA, and Yukon Territory, Canada, ranging from cold arctic mountains in the tundra biome to warmer interior mountains areas within the boreal biome. We used the annual maximum Normalized Difference Vegetation Index (NDVI) data from the 250-m MODIS NDVI product as a proxy of maximum growing season photosynthetic activity. The long-term (16-year) and interannual pattern of maximum NDVI was investigated with respect to elevation, July temperature, and July precipitation classes within four climatic mountain regions. The July temperature lapse rate was consistently linear, whereas the long-term maximum NDVI lapse rate was nonlinear. At lower elevations, the high-precipitation region had the highest NDVI, whereas the interior mountains region had the highest NDVI at higher elevations. The long-term maximum NDVI was negatively correlated with July precipitation for areas with July temperature below 12°C. Above 12°C, NDVI was positively correlated with July precipitation, with the greatest rate of NDVI increase with precipitation at the warmest July temperature class. The pattern of interannual peak NDVI with respect to July temperature was not as strong as the long-term pattern; however, the only interannual negative correlation between peak NDVI and July temperature was at lower elevations within the interior mountains. We concluded that among a regional climatic gradient of mountain areas, low growing season temperature and length were likely constraining vegetation productivity, and lower growing season moisture may be an important constraint at the warmest interior mountains region.

The normalized difference vegetation index (NDVI) is a crucial variable in Earth system science. While numerous kilometer-scale NDVI satellite products exist, fine-resolution products, particularly those derived from the extensive Landsat data archive, remain scarce. Producing fine-resolution NDVI from Landsat faces two primary challenges: frequent cloud cover causing irregular data acquisition, and terrain-induced radiometric distortion affecting spectral signal accuracy in complex terrain regions. This study presents a novel Terrain-Adjusted Local-Enhanced Spatiotemporal Fusion (TALESF) method that integrating Landsat surface reflectance and Global LAnd Surface Satellite (GLASS) NDVI product (V6) to generate 30-m, 8-day NDVI without terrain effects. The proposed method consists of four steps. First, the path length correction (PLC) method was employed to generate topographic effects-free Landsat surface reflectance data. Second, the Landsat clear-sky NDVI was estimated using a random forest (RF) model trained on terrain-corrected Landsat surface reflectance and GLASS NDVI. Third, for cloudy pixels, seasonal curves were constructed to identify similar pixels, then trend equations were fitted from all similar pixels to perform initial reconstruction of missing NDVI values. Finally, multiple NDVI reconstruction values were combined using contribution coefficients calculated from GLASS NDVI to generate the final cloudy-sky NDVI. The performance of TALESF was evaluated across various study sites with diverse land cover types. Results showed that the NDVI reconstructed by TALESF exhibited strong spatiotemporal continuity and accurately captured fine-scale surface features, and effectively resolved topographic effects at the 30-metre scale. Relative to other representative reconstruction algorithms, TALESF achieved an average error reduction of 17.44% to 31.33%. Large-scale reconstruction efficiency comparison over a 30 km × 30 km region demonstrates that our method requires only 6 seconds, achieving a significantly faster reconstruction speed compared to most approaches. As a demonstration, a 30-m, 8-day NDVI dataset was generated for the Sichuan-Yunnan ecological barrier region from 2013 to 2021, showing seamless spatial and temporal continuity, compared with GLASS NDVI, the average coefficient of determination (R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>) exceeded 0.90. Overall, the TALESF provides an efficient and accurate solution for reconstructing high spatiotemporal resolution NDVI datasets over large-scale and topographically complex regions.

. This study, based on the analyses of long-term discharge and Normalized Difference Vegetation Index (NDVI) data, revealed a strong seasonal consistency between NDVI and discharge over the Mackenzie River Basin in Canada. The flow–NDVI association is particularly strong in the early growing season (May to the 1st half of June). During this period, discharge rapidly rises and reaches the peak, whereas NDVI increases around the 1st half of May and reaches the maximum at the 2nd half of July. In the mid- and late summer, both discharge and NDVI decline gradually. Correlation analyses identify 2 sensitive periods, i.e., May to June and the 2nd half of July to the 1st half of September, when NDVI significantly responds to discharge variations. In the first period, the half-month NDVI highly correlates to the 1st half of May discharge, indicating that spring flow has a strong influence on vegetation growth in the early growing season. Spatially, almost all of the basin shows a high correlation, except Mackenzie and the Rocky Mountains and the region near the eastern edge of the basin. For the 2nd period, from the 2nd half of July to the 1st half of September, the NDVI relates closely to discharge with lags of 0–5 half-months. Trends analyses suggest river discharge increased during 1982 to 2006 in most seasons except summer. The NDVI trends during the growing season (May to September) clearly correspond to discharge changes. Examination of extreme flow years and corresponding NDVI conditions over the basin also reveal that a lower runoff was associated with a lower basin NDVI with an earlier maximum, whereas the higher flow was linked with a higher NDVI and a longer growing season.

The Bosten Lake, as an ecological key hub in the arid region of Northwest China, has a relatively unique ecological environment, making it challenging to maintain ecological balance. Studying the dynamic changes of the normalized difference vegetation index (NDVI) in the Bosten Lake Basin and its driving factors is of great significance for maintaining the stability and sustainable development of the basin's ecosystem. Based on Landsat data from 2001 to 2023, the NDVI values of the Bosten Lake Basin were calculated. The Mann-Kendall trend significance test, Sen's slope estimation method, and Hurst index were used to analyze the spatiotemporal dynamic changes of NDVI in the Bosten Lake Basin, and the relationship between climatic factors and NDVI was explored. The results showed that: ① The annual maximum NDVI in the Bosten Lake Basin generally showed an increasing trend, with a growth rate of 0.003 3 a-1. The spatial distribution characteristics of NDVI were relatively obvious, mainly dominated by high vegetation coverage, with 52.18% of the area showing an increasing trend. ② Seasonally, the NDVI during the growing season showed an increasing trend, with the highest NDVI in summer and the lowest in spring, and the trend of summer NDVI changes was consistent with the annual maximum NDVI changes. ③ The Hurst index predicted that 34.72% of the area in the Bosten Lake Basin would show a degradation trend in NDVI, while 65.28% would show an improvement trend. ④ The annual maximum NDVI in the Bosten Lake Basin from 2001 to 2020 was positively correlated with rainfall, temperature, sunshine hours, and evaporation and significantly correlated with sunshine hours and total evaporation, with correlation coefficients of 0.374 and 0.494, respectively. Therefore, the NDVI in the Bosten Lake Basin has shown an improving trend over the past 23 years, positively correlated with climatic factors. This study provides a scientific basis for the ecological environment construction, ecosystem management, and ecological balance maintenance in the Bosten Lake Basin.

This paper takes the central area of Shenzhen as an example to explore the correlation and differences between 2D and 3D green spaces on urban roads during the summer of 2023. By collecting street view image data and using convolutional neural networks for image semantic segmentation, the Green View Index (GVI) was calculated and combined with the Normalized Difference Vegetation Index (NDVI) for analysis. The results show that the road greening levels in Nanshan District, Futian District, and Luohu District of Shenzhen are relatively high, with GVI exceeding 25%. The Pearson correlation coefficient between the 2D and 3D greening data is 0.5818, indicating a moderate correlation. By analyzing four typical greening scenarios (high NDVI and high GVI, high NDVI and low GVI, low NDVI and high GVI, and low NDVI and low GVI), the study found specific reasons for the differences in green data in different dimensions; the analysis revealed that factors such as building height, density, and elevated transportation facilities significantly affect the accuracy of NDVI in urban spaces. The study suggests that in urban greening assessments, the complementarity and differences between street view data and remote sensing data should be comprehensively considered to improve the accuracy and comprehensiveness of the analysis.

ABSTRACTThe normalized difference vegetation index (NDVI) has been widely used to quantify vegetation by measuring the difference between near-infrared (NIR) and red light. Measuring NDVI throughout a growing season helps to evaluate the effect of continuous phenological and morphological changes on grain yield. A 2-year field study was conducted to characterize plant response to water stress in 20 winter wheat (Triticum aestium L.) genotypes during the season based on their NDVI values under the dryland and irrigated conditions. In addition, final biomass and yield were measured at maturity. The 2018 season was extremely dry with only 23 mm of precipitation, whereas 2016 was more favorable for wheat production with 315 mm seasonal precipitation. Except in a severe drought condition (2018, dryland), NDVI values increased from early spring to mid-season (anthesis) and decreased from mid-season to physiological maturity, indicating gradual leaf senescence. There was a significant (P = 0.05) positive correlation between NDVI and grain yield, especially for NDVI values after jointing. However, under the severe drought condition of 2018 (dryland), NDVI often did not show a strong relationship with grain yield. Even genotypes with higher NDVI at early growth stages ended up with lower yield because of the severe water stress at later growth stages. Hence, the use of NDVI is not suggested in screening genotypes for yield under extreme weather conditions.

Red tip disease on pineapple (Ananas comosus) was first recognized about 20 years ago in a commercial pineapple stand located in Simpang Renggam, Johor, Peninsular Malaysia. Since its discovery, there has been no confirmation on the causal agent of red tip disease. The epidemiology of red tip disease is still not fully understood. However, based on disease symptoms and field transmission mode, red tip disease seems to be strongly associated with viral infection. The aim of this work was to assess the feasibility of using an optical sensor to estimate red tip disease severity. This work was performed in a commercial pineapple plantation located in Simpang Renggam, Johor. Four observation plots bearing pineapple variety SR36 were demarcated based on crop growth stage. Each plot comprised a total of eighty corresponding measurements of percent Disease Severity (% DS) and Normalized Difference Vegetation Index (NDVI). Our data showed a strong correlation between % DS and NDVI. The 7- and 11-month plantings registered a correlation coefficient (r) of -0.83 and -0.88, respectively. The negative correlation infers that NDVI increases when disease severity is low. This is expected since healthy leaves reflect more near-infrared light and less visible light which results in a higher NDVI. The regression of NDVI on % DS for the 7-month planting was explained by: % DS = 181.6 - 185.6*NDVI. Meanwhile, the regression of NDVI on % DS for the 11-month planting was explained by: % DS = 213.2 - 219.8*NDVI. The linear fit between measured % DS and estimated % DS from the 7-month and 11-month plantings was relatively strong. This work has demonstrated that NDVI is a reliable predictor of % DS in pineapple.

The normalized difference vegetation index (NDVI) is widely used in global environmental and climatic change research. However, the 1 km Moderate Resolution Imaging Spectroradiometer (MODIS) is too coarse to quantify changes in heterogeneous landscapes. On the other hand, the 30 m charge-coupled device (CCD) sensor on the Chinese environment satellite (HJ-1) is severely affected by weather, which limits its use in studying the biophysical processes evolving rapidly during the growing season. In cloudy areas, the problem is compounded; only a few images can be obtained for the whole year. It is therefore impossible to obtain the high temporal spatial resolution NDVI required in some applications. To solve this problem, the continuous correction (CC) data assimilation method was proposed to produce high temporal spatial resolution NDVI by combining the advantages of the MODIS temporal information and the CCD spatial information. The MODIS 16 day compositing/8 day windows Nadir BRDF-Adjusted Reflectance and the CCD reflectance were used to predict 8 day/30 m NDVI for the Heihe River basin, China, in 2009. Comparison of predicted data with field data showed that the two were in good agreement. The method demonstrated feasibility, and the NDVI produced provided better vegetation information. The performance of CC depended on the acquisition time and amount of the CCD images.

Can palm date plantations and oasification be used as a proxy to fight sustainably against desertification and sand encroachment in hot drylands?

ABSTRACTA regional framework for a spatial and temporal distributed assessment of time series trends in the hydrological variable and its related ecological factors of an arid area was presented in this research. To achieve this, we tested the Surface Energy Balance System (SEBS) algorithm for estimating evapotranspiration (ET) in regional scale and the result was further validated by water budget. The ET assessment was applied for the Yinchuan and Weining (YW) Plains (China), the upstream areas of the Yellow River. Moreover, we analysed the recent trends (from year 2001 to 2014) in actual ET, normalized difference vegetation index (NDVI), farmland and wetland using a combination of remote sensing and ground observations. The results illustrated that the yearly ET of 78% areas has no change during the study period and the areas with decreasing ET are larger than the areas with increasing trend. The highest decreasing rate is observed in urban areas and the value is –20 mm year–1, while the rate of increasing trend is especially higher in the wetlands reaching around 60 mm year–1. This phenomenon can be explained by changes in NDVI, farmland and wetland. The distribution and magnitude of NDVI trends shows that the higher NDVI (NDVI > 0.4) area is occupied 56% and the farmland (NDVI > 0.55) covered about 35% of the YW Plains. The increasing trends of mean NDVI is mostly observed in farmland and shrub covers, while the decreasing NDVI areas are mainly wetlands and urban area. The emerging image showed that the greening trend of vegetation and variation of evapotranspiration in the YW Plains are related to land-cover changes and to the adjustment of crop pattern for agriculture. The increasing of wetland area is also believed as a cause related to evapotranspiration change. Such spatiotemporally distributed analysis in regional level is important for water management at this scale, which can be also applied to other similar areas.

Arthritis is a common health issue among middle-aged and older adults, significantly impacting their quality of life. While previous studies have explored various risk factors for arthritis, the relationship between green space exposure and arthritis risk remains underexplored. This study aims to investigate the correlation between green space exposure, as measured by the Normalized Difference Vegetation Index (NDVI), and arthritis risk among middle-aged and older adults in China using a cross-sectional approach. Data for the present study were extracted from the 2015 wave of the China Health and Retirement Longitudinal Study (CHARLS), focusing specifically on middle-aged and older adults aged 45 years and above. Greenness exposure was quantified using the NDVI. Generalized linear models were used to assess the association between NDVI and arthritis. Climatic variables (relative humidity, precipitation) and metabolic equivalents were evaluated as correlates and potential mediators of this relationship. The study included a total of 7,985 participants, of whom 3,519 had arthritis and 4,466 did not. In the fully adjusted model, NDVI showed a positive correlation with arthritis. Specifically, the odds ratio (OR) of arthritis for each interquartile range (IQR) increase in NDVI was 1.14 (95% CI: 1.02–1.27). Additionally, annual precipitation, annual relative humidity, and metabolic equivalents all showed positive associations with arthritis prevalence. Further mediation analysis indicated that annual precipitation significantly mediated the relationship between NDVI and arthritis, with a proportion mediated of 5.31%. Higher NDVI was associated with a higher prevalence of arthritis, and annual precipitation partly explained this association. The findings suggest that environmental factors, including greenery and climate, may be considered in future strategies aimed at understanding and addressing joint disease burdens. The study was approved by the Institutional Review Board of Peking University (Code: IRB00001052-11015) and conducted in accordance with the Declaration of Helsinki, with written informed consent obtained from all participants. • Based on CHARLS 2015 data, a per IQR increase in NDVI was associated with a 14% higher prevalence of arthritis. • Mediation analysis indicated that annual precipitation partially accounted for the observed association between NDVI and arthritis prevalence. • Regions with higher levels of green space may consider integrating environmental factors, such as greenery and climate, into joint disease prevention and management strategies.