Difference Vegetation Index Research Articles

Assessments of the impacts of environmental factors on vegetation cover at gas flaring sites in the Niger Delta, Nigeria.

The application of Satellite Earth Observation (EO) data provides the possibility of large scale mapping for the assessment of the effects of environmental factors on vegetation cover at the flaring sites. Twenty oneLandsat 7 Enhanced Thematic Mapper Plus (ETM+) data, and four Landsat 8 Operational Land Imager and Thermal Infrared Sensor (OLI-TIRS) data dated from 21/04/2000 to 05/02/2022 with < 3 % cloud cover were employed to study 11 gas flaring sites in Rivers State, Nigeria. MATLAB code was developed for data processing and analysis. Normalized Differential Vegetation Index (NDVI) was computed from the atmospherically corrected multispectral bands (1-4) for Landsat 7, and bands (2-5) for Landsat 8. Change in NDVI was computed as(δNDVI450-60)min the N, E, S and W directions which is the difference between NDVI at 450 m and 60 m distance from the flare stack. The available environmental factors (Facility size, flare stack height and time i.e. year, month and day) were applied to the (δNDVI450-60m) in the 4 cardinal directions. Pairwise linear and multiple regression statistical analyses were adopted to investigate the relationships between each of the (δNDVI450-60)mN, (δNDVI450-60)mE, (δNDVI450-60)mS and (δNDVI450-60)mW and facility size, stack height and time. The results show that only 12 % of the variance in (δNDVI450-60)mN is explained by the available data. Therefore, it can be concluded that the combination of the facility size, flare stack height and time accounted for only 12 % of the results.

Seasonal Variability of Golden Tides (Pylaiella littoralis, Phaeophyceae) and Nutrient Dynamics in a Potentially Eutrophic Intertidal Estuary

Understanding macroalgal bloom development is crucial for managing eutrophication and protecting estuarine ecosystems. In this study, brown macroalgal blooms (i.e., golden tides) were identified in a potentially eutrophic temperate estuary (NW Ireland). Pylaiella littoralis (Phaeophyceae, Ectocarpales) was monitored at low tide over seven sampling occasions between June 2016 and August 2017. In situ biomass, tissue nutrients (nitrogen (N) and phosphorus (P)), and isotopic signature (δ15N contents) were measured, and relations with environmental drivers were explored. Difference Vegetation Index (NDVI) values from Sentinel-2 satellite imagery were used to assess the spatiotemporal dynamics of P. littoralis biomass (2016–2022). The results indicated that NDVI attributed to golden tides were lowest in 2022, during summer (coinciding with high temperatures and high rainfall) and at the lower shore on the right margin of an entering river. The highest tissue P content was recorded in April 2017, coinciding with in situ biomass peaks (spring–early summer), suggesting elevated P demand. Tissue N content (>2%) and N:P ratios (10–30) indicated occasional P limitation but no N limitation. δ15N data were very low and it was not possible to identify any primary N source. These findings highlight the importance of nutrient management in mitigating golden tides, addressing eutrophication, and preserving estuarine ecosystems.

Mapping wildfires in Canada with Landsat MSS to extend the National Burned Area Composite (NBAC) time series back to 1972

Background Satellite imaging has improved burned area mapping; however, few studies have taken advantage of the Multi-Spectral Scanner (MSS) in early Landsat satellites, which started acquiring data 10 years earlier than Thematic Mapper (TM). Aims To expand Canada’s National Burned Area Composite (NBAC) annual time series back to 1972 using MSS data and report annual statistics and national trends for 1972–2022. Methods Pre- and post-fire image composites were created using an improved collection of MSS data available from the Google Earth Engine. A Normalized Difference Vegetation Index (NDVI) difference image was adaptively thresholded to extract burned areas, which were then vectorised. To assess accuracy, MSS fire polygons were compared with TM in a year of overlap. Key results Compared with TM, MSS polygons overestimated burned area by 5.6% when the relativised differenced NDVI was used, with significant upward trends for number of fires > 200 ha, fire season length and mean duration of fires. Conclusions MSS is a valuable data source for retrospective mapping of boreal and temperate forest fires where data from finer-resolution sensors are lacking. Implications After the addition of MSS-mapped fires, NBAC is the longest satellite-based time series of annual burned area from individually mapped fires in the world.

Estimation of Water Interception of Winter Wheat Canopy Under Sprinkler Irrigation Using UAV Image Data

Canopy water interception is a key parameter to study the hydrological cycle, water utilization efficiency, and energy balance in terrestrial ecosystems. Especially in sprinkler-irrigated farmlands, the canopy interception further influences field energy distribution and microclimate, then plant transpiration and photosynthesis, and finally crop yield and water productivity. To reduce the field damage and increase measurement accuracy under traditional canopy water interception measurement, UAVs equipped with multispectral cameras were used to extract in situ crop canopy information. Based on the correlation coefficient (r), vegetative indices that are sensitive to canopy interception were screened out and then used to develop canopy interception models using linear regression (LR), random forest (RF), and back propagation neural network (BPNN) methods, and lastly these models were evaluated by root mean square error (RMSE) and mean relative error (MRE). Results show the canopy water interception is first closely related to relative normalized difference vegetation index (R△NDVI) with r of 0.76. The first seven indices with r from high to low are R△NDVI, reflectance values of the blue band (Blue), reflectance values of the near-infrared band (Nir), three-band gradient difference vegetation index (TGDVI), difference vegetation index (DVI), normalized difference red edge index (NDRE), and soil-adjusted vegetation index (SAVI) were chosen to develop canopy interception models. All the developed linear regression models based on three indices (R△NDVI, Blue, and NDRE), the RF model, and the BPNN model performed well in canopy water interception estimation (r: 0.53–0.76, RMSE: 0.18–0.27 mm, MRE: 21–27%) when the interception is less than 1.4 mm. The three methods underestimate the canopy interception by 18–32% when interception is higher than 1.4 mm, which could be due to the saturation of NDVI when leaf area index is higher than 4.0. Because linear regression is easy to perform, then the linear regression method with NDVI is recommended for canopy interception estimation of sprinkler-irrigated winter wheat. The proposed linear regression method and the R△NDVI index can further be used to estimate the canopy water interception of other plants as well as forest canopy.

Wildfire assessment using machine learning algorithms in different regions

BackgroundClimate change and human activities are two main forces that affect the intensity, duration, and frequency of wildfires, which can lead to risks and hazards to the ecosystems. This study uses machine learning (ML) as an effective tool for predicting wildfires using historical data and influential variables. The performance of two machine learning algorithms, including logistic regression (LR) and random forest (RF), to construct wildfire susceptibility maps is evaluated in regions with different physical features (Okanogan region in the US and Jamésie region in Canada). The models’ inputs are eleven physically related variables to output wildfire probabilities.ResultsResults indicate that the most important variables in both areas are land cover, temperature, wind, elevation, precipitation, and normalized vegetation difference index. In addition, results reveal that both models have temporal and spatial generalization capability to predict annual wildfire probability at different times and locations. Generally, the RF outperforms the LR model in almost all cases. The outputs of the models provide wildfire susceptibility maps with different levels of severity (from very high to very low). Results highlight the areas that are more vulnerable to fire. The developed models and analysis are valuable for emergency planners and decision-makers in identifying critical regions and implementing preventive action for ecological conservation.

Dynamical systems-inspired machine learning methods for drought prediction

Drought is a naturally occurring phenomenon that affects millions of people and results in billions of dollars in damages each year, with impacts expected to worsen due to climate change. At the same time, definitions of drought are nebulous, and extant quantitative drought indicators suffer from short prediction horizons. One such indicator is the Normalized Vegetation Difference Index (NDVI), which measures photosynthetic activity, making it a strong proxy for vegetation density. Recent studies have identified chaotic attractors in satellite-derived NDVI time-series, suggesting a dynamical systems framework may be helpful for time-series prediction of NDVI. In this study, we compare the performance of a mechanistic model and two physics-informed machine learning methods (Sparse Identification of Nonlinear Dynamics [SINDy] and reservoir computing) on the prediction of NDVI time-series data in drought-prone regions of Kenya. We find that SINDy, a sparse polynomial modelling architecture, narrowly outperforms the other two methods with the use of precipitation data, while also retaining some of the interpretability of the mechanistic model. We also find that none of the methods perform as well in the regions in which the chaotic NDVI attractors were originally identified. We conclude by proposing more sophisticated extensions to the methods presented here, both with and without the availability of precipitation data, that draw on the existing dynamical systems and machine learning literature to enable better quantitative predictions of key drought indicators.

Analysis and prediction of land surface temperature with increasing urbanisation using satellite imagery

The unplanned growth of urbanization in towns and cities has led to variations in Land Surface Temperature (LST) as the green lands are converted into impervious structures without land cover management. In this study, an effort is made to study the transformational change in natural land cover area over the years and its impact on LST in Ernakulum District of Kerala, India. As per the current statistics from one of the reports on “Observed Rainfall Variability and Changes Over Kerala State”, by Indian Metrological Department in January 2020 shows that there is a significant decreasing trend in rainy days in many districts of Kerala which has resulted in highest temperature records in recent years. To understand the change in temperature trends in the district, Landsat data is collected for four different years 2005, 2010, 2015 and 2020 that maps Land Use and Land Cover (LULC) pattern for vegetation cover and built-up areas. It is important to interpret LULC maps as converting the vegetative land in built-up areas leads to multiple reflecting surfaces and temperature trapping which serves as the most direct way to understand the influence of global warming. The major merit of this research is (i) to interpret the temporal changes in LULC for categorizing the images in different land covers, (ii) to analyze Urban Thermal Field Variance Index (UTFVI) to quantify the urban heat island (UHI) effect in the region, (iii) to assess change in temperature by analyzing the spatio-temporal variations in mean temperatures for different land cover classes, and (iv) to analyze the trend of LST wrt to vegetation spectral index i.e., Normalized Differential Vegetation Index (NDVI) and spectral building index i.e., Normalized Difference Building Index (NDBI) to predict the percentage change in temperature in successive years using the widely used regression model. The computational simulation findings show that the percentage area of vegetated land decreases from 47.91 % to 29.04 % and the LST change analysis observed for years from 2005 to 2020 is 2.55 °C. For built up land, the percentage area is increased from 6.50 % to 15.27 % and the change in LST observed from year 2005–2020 is 4.82 °C which is a significant rise in temperature. The overall accuracy achieved for four respective years comes out to be 93, 89, 90, and 92 %. It has been observed from the analysis, that there is a change in temperature over the period of time from 2005 to 2020 b 3.45 °C. This is due to unplanned use of land cover classes that show considerable change in LULC maps that can be seen in the simulated results for a given study area. If the rate of change in area appeared to constantly change in this manner, then there is a possibility of further increase in land surface temperature and that will contribute in increase of temperature. The rise in mean LST from year 2020–2025 would be 0.5 °C and 1.0 °C for year 2030.

Deep learning modeling to assess surface temperature and greenery impact on emergency room access

Abstract The escalating land surface temperature is a key environmental indicator with potential repercussions on human health. An artificial NN model was built to predict the number of ER accesses as a dependent variable, to establish the predictive power and interactions of land surface temperature and normalized differential vegetation index(NDVI), which is used to measure urban greenery.A map of Taranto was built by vector files on the Apulia region website and processed using R Studio 2023.06.2.The vector file containing the mapping of the city of Taranto was processed to obtain a 200mx200m grid of the entire surface.The Local Health Authority of Taranto provided indications of the residences of ER accesses, and coordinates were merged to gridded vector file to obtain the average of ER accesses and the socio demographic features per single grid unit. NDVI and surface temperature were averaged for July 2023 using images from Landsat 8(30m) and merged to the vector providing an average value of temperature and NDVI index per single quadrant. The dataset was divided into two db according to an 80/20 ratio respectively for the training and test dataset.A NN model was built on dichotomous value (above/below median) for each quadrant (6513 units) with hyperparameter tuning technique using the accuracy to select the best model.A MOC model was built to reduce the probability of NN detection by at least 40% in a randomly selected subject.A MOC model was built considering sociodemographic variables as fixed features and an epsilon of 0 for 175 generations and an ICE curves population initialization strategy. NNET accuracy value was 0.849 and 0.841 in training and testing, suggesting a good fitting of the model.Relative change plots were adopted to show the amount and the direction of generated counterfactuals, to reduce grid unit prediction to be over median.LST decreasing and NDVI score increasing were associated with a reduction of classification probability of grid unit. Key messages • Rising land surface temperature is a critical environmental indicator with potential impacts on human health. • Artificial neural network models perform well in predicting the number of ER accesses with respect to land surface temperature and NDVI, which is used to measure urban greenery.

Monitoring of Heracleum sosnowskyi Manden Using UAV Multisensors: Case Study in Moscow Region, Russia

Detection and mapping of Sosnowsky’s hogweed (HS) using remote sensing data have proven effective, yet challenges remain in identifying, localizing, and eliminating HS in urban districts and regions. Reliable data on HS growth areas are essential for monitoring, eradication, and control measures. Satellite data alone are insufficient for mapping the dynamics of HS distribution. Unmanned aerial vehicles (UAVs) with high-resolution spatial data offer a promising solution for HS detection and mapping. This study aimed to develop a method for detecting and mapping HS growth areas using a proposed algorithm for thematic processing of multispectral aerial imagery data. Multispectral data were collected using a DJI Matrice 200 v2 UAV (Dajiang Innovation Technology Co., Shenzhen, China) and a MicaSense Altum multispectral camera (MicaSense Inc., Seattle, WA, USA). Between 2020 and 2022, 146 sites in the Moscow region of the Russian Federation, covering 304,631 hectares, were monitored. Digital maps of all sites were created, including 19 digital maps (orthophoto, 5 spectral maps, and 13 vegetation indices) for four experimental sites. The collected samples included 1080 points categorized into HS, grass cover, and trees. Student’s t-test showed significant differences in vegetation indices between HS, grass, and trees. A method was developed to determine and map HS-growing areas using the selected vegetation indices NDVI > 0.3, MCARI > 0.76, user index BS1 > 0.10, and spectral channel green > 0.14. This algorithm detected HS in an area of 146.664 hectares. This method can be used to monitor and map the dynamics of HS distribution in the central region of the Russian Federation and to plan the required volume of pesticides for its eradication.

Estimation, Spatiotemporal Dynamics, and Driving Factors of Grassland Biomass Carbon Storage Based on Machine Learning Methods: A Case Study of the Hulunbuir Grassland

Precisely estimating the grassland biomass carbon storage is vital for evaluating grassland carbon sequestration potential and the monitoring and management of grassland resources. With the increasing intensity of climate change (CC) and human activities (HA), it is necessary to explore spatiotemporal variations in biomass carbon storage and its response to CC and HA. In this study, we focused on the Hulunbuir Grassland, utilizing sample plots data, MODIS data, environmental factors (terrain, soil, and climate), location factor, and texture characteristics to assess the performance of four machine learning algorithms: random forest, support vector machine, gradient boosting decision tree, and extreme gradient boosting in estimating grassland aboveground biomass (AGB). Based on the optimal model combined with root-shoot ratio data, grassland distribution data, and carbon content coefficients, the spatiotemporal characteristics and driving factors of biomass carbon storage from 2001–2022 were analyzed. The results showed that (1) the random forest achieved the highest prediction accuracy for grassland AGB, making it appropriate for AGB estimation in the Hulunbuir Grassland. (2) The spectral indices were the key variables of the grassland AGB, especially the enhanced vegetation index and difference vegetation index. (3) The 22-year average total biomass (TB) of the study area was 1037.10 gC/m2, of which the 22-year average AGB was 48.73 gC/m2 and 22-year average belowground biomass was 988.37 gC/m2, showing a spatial distribution feature of gradual increase from west to east. (4) From 2001–2022, TB carbon storage showed an insignificant growth trend (p > 0.05). The 22-year average carbon storage of TB was 72.34 ± 18.07 gC. (5) Climate factors were the main driving factors for the spatial pattern of grassland TB carbon density, while the combined effects of CC and HA were the main contributors to the interannual increase in grassland TB carbon density.

Remote sensing retrieval of surface soil moisture in Mu Us Sandy Land based on optical trapezoid model

Abstract Maowuosu sandland ecosystem is fragile, and moisture is a key factor restricting the growth and development of sandland plants and ecological construction in semi-arid areas. Therefore, this study constructed the eigenspace based on the data of the 4th period of 2016, fitted the dry and wet edge equations of the eigenspace, calculated the OPTRAM, and utilized the measured in situ soil moisture data from various depths during the corresponding period. The OPTRAM was regressed to construct a model for estimating soil moisture. This model was then subjected to a series of validation procedures to ensure its accuracy. The coefficients for the shortwave infrarouges conversion reflection coefficient (STR) - standardized differential vegetation index (NDVI) feature space dry and wet edge fits increased with the increase of the month, where the dry and the R2 for the wet side in September was 0.88 and 0.87, respectively. OPTRAM and the measured soil moisture content data in the surface layer were all correlated to some extent, with correlation coefficients above 0.45. The OPTRAM model is more accurate than other models in inverting in situ moisture content at the 0∼10 cm depths within this area.

Multi-spatial Resolution Imagery to Estimate Above-Ground Carbon Stocks in Mangrove Forests

Mangroves are a type of vegetation that can absorb carbon and have an essential role in controlling CO2 levels in the atmosphere. Mangroves can absorb carbon better than terrestrial ecosystems because of their ability to bury carbon in sediment. This research aims to compare and measure the carbon stock content above the surface of mangroves in the field using multi-spatial resolution imagery, namely, Landsat 8 OLI, Sentinel 2A, and Planetscope. Field carbon calculations were carried out using the allometric method based on mangrove species. The calculation results are then linked through regression analysis with the vegetation index Difference Vegetation Index (DVI) results. The total carbon obtained from PlanetScope imagery was 535.27 tons, Sentinel 2A imagery was 549.23 tons, and Landsat 8 OLI imagery was 533.57 tons. Among the three images used, based on Sentinel 2A statistical analysis reflects the possibility of overfitting or the best with higher r and R2 values in the calculations. However, based on SE accuracy tests, PlanetScope has better accuracy than the other two images. Apart from that, the accuracy test results using a 1:1 goodness of fit plot for each image, the distribution pattern of mangrove carbon stock estimates shows that the entire model in mapping mangrove carbon stocks is over-estimated. The overestimated results are possible because more objects around the mangrove, especially canopy density, are recorded by remote sensing sensors compared to tree diameter as input for field carbon results.

Green Space Cooling Effect and Relation to Mitigate Surface Urban Heat Island Effect of Metropolitans Cities of India

Difference Vegetation Index (NDVI) to study vegetation's spatial distribution. However, MODIS thermal bands were employed to analyse Land Surface Temperature (LST) and city thermal properties. The findings show that 15.97% of Lucknow's total area is classified as a High potential SUHI zone, compared to 29.41%, classified as a Low potential SUHI zone. Jaipur has two possible SUHI zones: a high potential zone (12.69%) and a low potential zone (30.45%). In contrast, Ahmedabad exhibits an 18.37 per cent High potential SUHI Zone and a 27.62 per cent low potential SUHI Zone. Delhi exhibits a 14.98 per cent High potential SUHI Zone but is significantly higher at 39.97 per cent Low potential SUHI Zone. Analysis of LST distribution reveals correlations with vegetation cover, with areas abundant in greenery experiencing lower temperatures. This study emphasizes how crucial green infrastructure is to urban planning to improve thermal comfort in fast-urbanizing areas and reduce the negative consequences of urban heat islands.

Study on the applicability of FAI linear fitting model in the extraction of cyanobacterial blooms.

Currently, more and more lakes around the world are experiencing outbreaks of cyanobacterial blooms, and high-precision and rapid monitoring of the spatial distribution of algae in water bodies is an important task. Remote sensing technology is one of the effective means for monitoring algae in water bodies. Studies have shown that the Floating Algae Index (FAI) is superior to methods such as the Standardized Differential Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) in monitoring cyanobacterial blooms. However, compared to the NDVI method, the FAI method has difficulty in determining the threshold, and how to choose the threshold with the highest classification accuracy is challenging. In this study, FAI linear fitting model (FAI-L) is selected to solve the problem that FAI threshold is difficult to determine. Innovatively combine FAI index and NDVI index, and use NDVI index to find the threshold of FAI index. In order to analyze the applicability of FAI-L to extract cyanobacterial blooms, this paper selected multi-temporal Landsat8, HJ-1B, and Sentinel-2 remote sensing images as data sources, and took Chaohu Lake and Taihu Lake in China as research areas to extract cyanobacterial blooms. The results show that (1) the accuracy of extracting cyanobacterial bloom by FAI-L method is generally higher than that by NDVI and FAI. Under different data sources and different research areas, the average accuracy of extracting cyanobacterial blooms by FAI-L method is 95.13%, which is 6.98% and 18.43% higher than that by NDVI and FAI respectively. (2) The average accuracy of FAI-L method for extracting cyanobacterial blooms varies from 84.09 to 99.03%, with a standard deviation of 4.04, which is highly stable and applicable. (3) For simultaneous multi-source image data, the FAI-L method has the highest average accuracy in extracting cyanobacterial blooms, at 95.93%, which is 6.77% and 13.26% higher than NDVI and FAI methods, respectively. In this paper, it is found that FAI-L method shows high accuracy and stability in extracting cyanobacterial blooms, and it can extract the spatial distribution of cyanobacterial blooms well, which can provide a new method for monitoring cyanobacterial blooms.

Estimation of land surface temperature and LULC changes impact on groundwater resources in the semi-arid region of Madhya Pradesh, India

The land surface temperature (LST) changes influence on many factors such as land use and land cover (LULC), vegetation and water resources etc. Now a day’s urban population growth, industrial development and human activity are increased due to human migration and urban expansion. The surface temperature is very harmful to vegetation, groundwater level, and ecosystem health. Urban pollution growth and air pollution factor is also playing important role for increase and decrease the LST with climate change impact. Demand of drinking water are increases particular in the urban city due to the population growth and urban expansion, which all of this direct effect on surface and groundwater sources and resources. Hence we have been chosen the latest technologies such as remote sensing (RS), Geographic information System (GIS) and Google Earth Engine (GEE) are very effective for mapping, monitoring and assessment of spatial maps of LST, LULC, and NDVI (Normalised differential vegetation index) estimation. In this study, main focus on the LULC of 2011 and 2021 were classified using random forest (RF) algorithm, ML and remote sensing datasets. LULC were divided into four categories i. e. agricultural land, built up land, waterbody and waste land. For better understanding about the growth of LST, this study examines the association between LST and NDVI change, what vegetation condition impact on the LST. The main and important results have been found the built-up land and LST positive correlation due to increases both the factors in the urban area. LST increases gradually and its bad effect on the green land, water level and expansion of barren land. The range of LST is 43.60 °C to 45.30 °C. Less vegetation cover showing highest LST and vice versa. All of the LST, NDVI, and LULC direct effect on the groundwater availability in the area. This paper important result found the built-up land and LST both are increased in 2021, NDVI and LST having negative correlation. The results of study can very much useful for understanding the LST, NDVI and LULC, these factors what impact on groundwater availability in the study area.

Early-Stage Mapping of Winter Canola by Combining Sentinel-1 and Sentinel-2 Data in Jianghan Plain China

The early and accurate mapping of winter canola is essential in predicting crop yield, assessing agricultural disasters, and responding to food price fluctuations. Although some methods have been proposed to map the winter canola at the flowering or later stages, mapping winter canola planting areas at the early stage is still challenging, due to the insufficient understanding of the multi-source remote sensing features sensitive for winter canola mapping. The objective of this study was to evaluate the potential of using the combination of optical and synthetic aperture radar (SAR) data for mapping winter canola at the early stage. We assessed the contributions of spectral features, backscatter coefficients, and textural features, derived from Sentinel-2 and Sentinel-1 SAR images, for mapping winter canola at early stages. Random forest (RF) and support vector machine (SVM) classification models were built to map winter canola based on early-stage images and field samples in 2017 and then the best model was applied to corresponding satellite data in 2018–2022. The following results were obtained: (1) The red edge and near-infrared-related spectral features were most important for the mapping of early-stage winter canola, followed by VV (vertical transmission, vertical reception), DVI (Difference vegetation index), and GOSAVI (Green Optimized Soil Adjusted Vegetation Index); (2) based on Sentinel-1 and Sentinel-2 data, winter canola could be mapped as early as 130 days prior to ripening (i.e., early overwinter stage), with the F-score over 0.85 and the OA (Overall Accuracy) over 81%; (3) adding Sentinel-1 could improve the OA by about 2–4% and the F-score by about 1–2%; and (4) based on the classifier transfer approach, the F-scores of winter canola mapping in 2018–2022 varied between 0.75 and 0.97, and the OAs ranged from 79% to 86%. This study demonstrates the potential of early-stage winter canola mapping using the combination of Sentinel-2 and Sentinel-1 images, which could enable the large-scale early mapping of canola and provide valuable information for stakeholders and decision makers.

Optimising forest rehabilitation and restoration through remote sensing and machine learning: Mapping natural forests in the eThekwini Municipality

Forests are crucial in delivering ecosystem services that underpin human well-being and biodiversity conservation. However, these vital ecosystems are threatened by forest degradation and rapid urbanisation. This study addresses this challenge by proposing a comprehensive framework for mapping natural forests at the municipal scale. The framework integrates remote sensing techniques with machine learning algorithms to provide valuable insights into the extent of natural forests within the eThekwini Municipality. The study utilised Landsat 7, Landsat 8, and Landsat 9 satellite imagery to analyse and map the historical and current distribution of natural forests. Five spectral indices, namely, Normalized Differential Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Chlorophyll Index Green (CIG), Enhanced Vegetation Index (EVI), and Enhanced Vegetation Index-2 (EVI-2), which were calculated from Landsat bands, were employed in the analysis. Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), and Extreme Gradient Boosting (XGBoost) machine learning algorithms were used to model forest distribution. Accuracy was assessed through confusion matrices, Receiver Operating Characteristic (ROC) Curves, area under the ROC curve (AUC), and the F1 scores. LightGBM achieved the highest overall accuracy (90.76%), followed by CatBoost (89.56%) and XGBoost (84.34%). LightGBM also obtained the best F1 score (90.76%). These findings highlight LightGBM's effectiveness in classifying natural forests, making it the preferred model for mapping the historical extent of natural forests in the eThekwini Municipality. However, classifications based on Landsat 7 significantly underestimated the extent of natural forests within the study area, whereas Landsat 8 and Landsat 9 data revealed an increase in natural forests from 2015 to 2023. These findings will guide effective and targeted forest rehabilitation and restoration efforts, ensuring the preservation and enhancement of forest ecosystem services.

Genome‐Wide Association Studies Predicted Drought Stress Occuring at Anthesis and Post‐Anthesis Stages in Novel Diverse Germplasm of Bread Wheat (Triticum aestivum)

ABSTRACTThis study employed genome‐wide association studies (GWAS) to identify the crucial marker–trait associations (MTAs) for agronomic and physiological traits in bread wheat grown under full irrigation and 40% reduced irrigation. One hundred twenty‐four genotypes derived from three‐way crosses of landraces and synthetic bread wheat were evaluated for 2 years in the field conditions of CIMMYT Obregon, Mexico. Irrigation was not provided at anthesis and post‐anthesis stage for the drought treatment, and data of 12 traits were recorded. Most of the traits were reduced significantly under drought conditions except for vigour, wax and spike length (SL); genotypes were significantly different for the eight traits except for days to heading (DTH), number of grains spike−1 (NGS), normalized difference in vegetation index (NDVI) and canopy temperature depression (CTD); and differences were also significant for five traits between the years. Moreover, GY was significantly and negatively correlated with wax and CTD. Our GWAS results indicated 117 significant (p ≤ 0.001) MTAs distributed on all the wheat chromosomes except chromosomes 4B and 4D explaining 10%–21.5% of the phenotypic variation of the corresponding traits. Moreover, 22 MTAs were recorded for grain yield and explaining the phenotypic variations up to 14.7% with one common association under both irrigated and drought conditions. Additionally, we also identified the associations for NDVI, CTD and SL at chromosome 1B, suggesting that genotypes are sustaining superior grain yield through better values of traits like NDVI, CTD, and SL under the challenging conditions of anthesis and post‐anthesis drought stress.

Improving detection of wheat canopy chlorophyll content based on inhomogeneous light correction

Effectively improving the detection accuracy of wheat chlorophyll content is of great significance for the detection of photosynthetic capacity and growth status of wheat canopy. However, due to inhomogeneous light distribution issues in canopy, the existence of shaded and sun wheat leaves in wheat canopy has influence for spectral-based detection of chlorophyll content. Therefore, in order to improve detection of wheat canopy chlorophyll content, a light distribution correction method was proposed to correct intact leaves’ light distribution based on shaded and sun leaves in multispectral images. Firstly, R-G-NIR images were reconstructed to segment and analyze shaded and sun leaves of wheat. Secondly, Homomorphic Filter (HF) and Gamma light correction method was used to optimize shaded leaves’ light distribution. Then, the differential responses of 10 different types of vegetation indices in shaded, sun, original intact and corrected intact leaves were analyzed to screen chlorophyll-sensitive parameters based on Random Frog Method (RFM). Finally, Random Forest (RF), Support Vector Regression (SVR), and Partial Least Squares Regression (PLSR) were used to establish models for the detection of chlorophyll content in shaded, sun, original intact and corrected intact leaves of wheat, respectively. The results showed that the proposed light correction method reduced the inhomogeneous light and kept more uniform. Normalized difference vegetation index (NDVI), green normalized difference vegetation index (GNDVI), difference vegetation index (DVI), normalized redness intensity (NRI), and optimized soil-adjusted vegetation index (OSAVI) were selected as the optimal spectral variables. And the models after correction had higher accuracy than the models before correction. The wheat chlorophyll content model of corrected intact leaves based on RF had the highest accuracy, with a calibration set Rc2 of 0.816, RMSEc of 3.702, a validation set Rv2 of 0.804, RMSEv of 3.958, respectively. The research integrates the above results to improve detection of wheat canopy chlorophyll content, which provides technical support for the light distribution correction in multispectral images.

A framework for natural resource management with geospatial machine learning: a case study of the 2021 Almora forest fires

BackgroundWildfires have a substantial impact on air quality and ecosystems by releasing greenhouse gases (GHGs), trace gases, and aerosols into the atmosphere. These wildfires produce both light-absorbing and merely scattering aerosols that can act as cloud condensation nuclei, altering cloud reflectivity, cloud lifetime, and precipitation frequency. Uttarakhand province in India experiences frequent wildfires that affect its protected ecosystems. Thus, a natural resource management system is needed in this region to assess the impact of wildfire hazards on land and atmosphere. We conducted an analysis of a severe fire event that occurred between January and April 2021 in the Kumaun region of Uttarakhand, by utilizing open-source geospatial data. Near-real-time satellite observations of pre- and post-fire conditions within the study area were used to detect changes in land and atmosphere. Supervised machine learning algorithm was also implemented to estimate burned above ground biomass (AGB) to monitor biomass stock.ResultsThe study found that 21.75% of the total burned area burned with moderate to high severity, resulting in a decreased Soil Adjusted Vegetation Index value (> 0.3), a reduced Normalized Differential Moisture Index value (> 0.4), and a lowered Normalized Differential Vegetation Index (> 0.5). The AGB estimate demonstrated a significant simple determination (r2 = 0.001702) and probability (P < 2.2 10−16), along with a positive correlation (r ≤ 0.24) with vegetation and soil indices. The algorithm predicted that 17.56 tonnes of biomass per hectare burned in the Kumaun forests. This fire incident resulted in increased emissions of carbon dioxide (CO2; ~ 0.8 10−4 kg carbon h−1), methane (CH4; ~ 200 10−9 mol fraction in dry air), carbon monoxide (CO; 2000 1015 molecules cm−2 total column), and formaldehyde (HCHO; 3500 1013 molecules cm−2 total column), along with increased aerosol optical thickness (varying from 0.2 to 0.5).ConclusionsWe believe that our proposed operational framework for managing natural resources and assessing the impact of natural hazards can be used to efficiently monitor near-real-time forest-fire-caused changes in land and atmosphere. This method makes use of openly accessible geospatial data that can be employed for several objectives, including monitoring carbon stocks, greenhouse gas emissions, criterion air pollution, and radiative forcing of the climate, among many others. Our proposed framework will assist policymakers and the scientific community in mitigating climate change problems and in developing adaptation policies.