Soil Adjusted Vegetation Index Research Articles

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.

Multi-scale geographically weighted regression estimation of carbon storage on coniferous forests considering residual distribution using remote sensing data

The Above-Ground Carbon (AGC) is an important indicator reflecting the carbon sink function of forest ecosystems. The area of coniferous forests in China accounts for about 50 % of the national forest area. Accurately estimating the AGC of coniferous forests plays an important role in evaluating forest carbon sink function. This study takes coniferous forests in Chun’an, Zhejiang Province as an example, using Landsat 8 OLI as the remote sensing data source, and innovatively proposes a multi-scale Geographically Weighted Regression model (MGWR) combined with Co-Kriging (COK), namely MGWR-COK and Ordinary Kriging (OK), namely MGWR-OK, for AGC estimation. This method first processes Landsat8 OLI remote sensing data, extracts and screens variables, and then constructs an MGWR model with AGC survey samples to estimate AGC and calculate residuals; Afterwards, two models, COK and OK, were used to spatially estimate the residuals; Finally, the AGC estimation results are overlaid with the residual estimation results to obtain the spatial distribution of AGC in coniferous forests. The study indicates that: (1) The selected remote sensing feature variables such as Optimized Soil-Adjusted Vegetation Index (OSAVI), Normalized Difference Vegetation Index (NDVI), Entropy (B3_ent_1 and B2_ent_2), Correlation (B4_corr and B5_corr_2) of texture information, B754 with band combination and elevation have a significant impact on AGC estimation. (2) The AGC accuracy R2 estimated by MGWR-OK and MGWR-COK are 0.837 and 0.857, respectively, which are 6 % and 8 % higher than the MGWR model, and the root mean square error is also reduced by 10 % and 12 %, respectively. This indicates that the combination of MGWR and Kriging interpolation can effectively reduce its spatial estimation error. (3) The range of AGC values estimated by the MGWR-COK model is 0.189–62.591 Mg ∙ hm−2, with a mean of 28.795 Mg ∙ hm−2. The spatial distribution shows a characteristic of high in the southeast and low in the northwest, which is consistent with the actual situation in the study area.

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.

Machine Learning Monitoring Model for Fertilization and Irrigation to Support Sustainable Cassava Production: Systematic Literature Review

The manual and time-consuming nature of current agronomic technology monitoring of fertilizer and irrigation requirements, the possibility of overusing fertilizer and water, the size of cassava plantations, and the scarcity of human resources are among its drawbacks. Efforts to increase the yield of cassava plants &gt; 40 tons per ha include monitoring fertilization approach or treatment, as well as water stress or drought using UAVs and deep learning. The novel aspect of this research is the creation of a monitoring model for the irrigation and fertilizer to support sustainable cassava production. This study emphasizes the use of Unnamed Aerial Vehicle (UAV) imagery for evaluating the irrigation and fertilization status of cassava crops. The UAV is processed by building an orthomosaic, labeling, extracting features, and Convolutional Neural Network (CNN) modeling. The outcomes are then analyzed to determine the requirements for air pressure and fertilization. Important new information on the application of UAV technology, multispectral imaging, thermal imaging, among the vegetation indices are the Soil-Adjusted Vegetation Index (SAVI), Leaf Color Index (LCI), Leaf Area Index (LAI), Normalized Difference Water Index (NDWI), Normalized Difference Red Edge Index (NDRE), and Green Normalized Difference Vegetation Index (GNDVI).

Desert oasis vegetation information extraction by PLANET and unmanned aerial vehicle image fusion

Sparse vegetation is a key factor in maintaining the health and sustainability of oasis ecosystems under extreme drought conditions. Combining the advantages of both satellites and drones, using image processing and machine learning technology, it can efficiently and accurately extract information on the vegetation of desert oases, providing a scientific basis for ecological monitoring and management. Therefore, in this study, the Dariyabui natural oasis in the hinterland of the Taklamakan Desert, China, was used as the study area to fuse PLANET and UAV images to screen 19 feature factors from different data sources. The machine learning binary classification model was evaluated based on the overall accuracy (OA, %), kappa, balanced accuracy (BA, %), F1_score (F1, %), and Area Under Curve (AUC) values. The results were validated using aerial imaging data from different months. The results show that (1) the primary feature factors for extracting sparse ground vegetation information in a desert oasis include the soil-adjusted vegetation index (SAVI); modified soil-adjusted vegetation index (MSAVI); optimized soil-adjusted vegetation index (OSAVI); and the mean, entropy, contrast, homogeneity, and digital surface models (DSM). (2) The evaluation indices of the fused images in the vegetation information extraction were better than those of the original satellite images; the difference in the extraction effect with the original UAV images was not significant. (3) The random forest (RF) algorithm achieved the best classification accuracy in extracting sparse vegetation information (Kappa = 0.87, OA = 94.12 %, BA = 93.53 %, F1 = 92.13 %, and AUC = 0.967).

Combining proximal and remote sensing to assess 'Calatina' olive water status.

Developing an efficient and sustainable precision irrigation strategy is crucial in contemporary agriculture. This study aimed to combine proximal and remote sensing techniques to show the benefits of using both monitoring methods, simultaneously assessing the water status and response of 'Calatina' olive under two distinct irrigation levels: full irrigation (FI), and drought stress (DS, -3 to -4 MPa). Stem water potential (Ψstem) and stomatal conductance (gs) were monitored weekly as reference indicators of plant water status. Crop water stress index (CWSI) and stomatal conductance index (Ig) were calculated through ground-based infrared thermography. Fruit gauges were used to monitor continuously fruit growth and data were converted in fruit daily weight fluctuations (ΔW) and relative growth rate (RGR). Normalized difference vegetation index (NDVI), normalized difference RedEdge index (NDRE), green normalized difference vegetation index (GNDVI), chlorophyll vegetation index (CVI), modified soil-adjusted vegetation index (MSAVI), water index (WI), normalized difference greenness index (NDGI) and green index (GI) were calculated from data collected by UAV-mounted multispectral camera. Data obtained from proximal sensing were correlated with both Ψstem and gs, while remote sensing data were correlated only with Ψstem. Regression analysis showed that both CWSI and Ig proved to be reliable indicators of Ψstem and gs. Of the two fruit growth parameters, ΔW exhibited a stronger relationship, primarily with Ψstem. Finally, NDVI, GNDVI, WI and NDRE emerged as the vegetation indices that correlated most strongly with Ψstem, achieving high R2 values. Combining proximal and remote sensing indices suggested two valid approaches: a more simplified one involving the use of CWSI and either NDVI or WI, and a more comprehensive one involving CWSI and ΔW as proximal indices, along with WI as a multispectral index. Further studies on combining proximal and remote sensing data will be necessary in order to find strategic combinations of sensors and establish intervention thresholds.

Post-fire vegetation dynamics of a temperate mixed forest: An assessment based on the variability of Landsat spectral indices

Fire plays a critical role in nutrient cycling and species diversity but also causes severe disturbances to ecosystems. Despite remote sensing has emerged as a valuable tool to study wildfires, a lack of information regarding post-fire dynamics still remains for certain regions. This study investigated the post-fire dynamics of four burned sites in the temperate forest of Chihuahua, northern Mexico from 2009 to 2017, based on the variability of spectral indices under varied topographic conditions of aspects and slopes. The Normalized Difference Vegetation index (NDVI), Soil Adjusted Vegetation Index (SAVI), Normalized Burn Ratio (NBR), and Normalized Difference Water index (NDWI) were utilized to assess vegetation recovery on the burned sites. One-way ANOVAs and Tukey´s tests were performed to evaluate separately the effects of aspect and slope on the indices’ variability (p < 0.05). In general, the NDVI measured the highest values of the burned sites along the evaluated lapse while the NDWI indicated the lowest measures. Results indicated significant effects of aspect on NDVI and SAVI (p < 0.05), while slope significantly influenced the four evaluated indices (p < 0.05).That in turn showed northern aspects and steeper slopes to have the highest post-fire vegetation recoveries. Furthermore, aspect only affected the bi-annual variability of SAVI (p < 0.05). However, the NBR and NDWI showed higher magnitudes of change among periods than the SAVI (i. e., recovery and non-recovery). Besides registering a continuous recovery of the burned sites from the wildfire events to 2015, this study revealed the NDVI and SAVI as the most useful spectral indices for assessing post-fire vegetation dynamics in the region. Besides aspect and slope, future studies could focus on the inclusion of additional indicators to more effectively assess post-fire ecosystem dynamics in northern Mexico.

Artificial intelligence and remote sensing for spatiotemporal analysis and prediction of vegetation changes: a case study of El Oued, northeastern Algeria

This study investigates vegetation ecology and rangeland degradation in the arid and desert regions of northeastern Algeria from 2015 to 2023, with predictions extending to 2031. Utilizing remote sensing techniques, specifically Landsat 8 and Landsat 9 imagery, and the Modified Soil Adjusted Vegetation Index (MSAVI), we mapped and analyzed changes in vegetation cover. The QGIS MOLUSCE plugin facilitated spatiotemporal analysis, revealing significant natural and anthropogenic impacts on a study area. Less degraded rangelands have also seen an increase, from 44,110,116 hectares in 2015 to 48,481,851 hectares in 2023, due to drought, overgrazing, and socioeconomic pressures. With a slight decrease to 48,450,495 hectares projected for 2031. This suggests efforts in land rehabilitation and sustainable rangeland management are yielding positive results, though there remains room for improvement. The study recorded that Agricultural croplands have experienced a slight decrease from 1,404,153 hectares in 2015 to 1,350,693 hectares in 2023. However, a modest increase to 1,587,242 hectares is projected by 2031. The findings indicate that Oases date palm areas have increased from 1,287,342 hectares in 2015 to 1,630,197 hectares in 2023, with further growth to 1,816,296 hectares anticipated by 2031. Our research highlights the critical role of remote sensing in monitoring vegetation dynamics within arid and desert ecosystems. The methodology provides a robust framework for similar studies, emphasizing the necessity for ongoing monitoring using advanced télédétection technologies. To mitigate further degradation and preserve these fragile ecosystems, the implementation of sustainable land management practices is essential.

Exploration of the utilization of a new land degradation index in Lake Ebinur Basin in China

Land degradation significantly impacts regional economic development and food security, particularly in arid river basins where soil and water conservation is crucial. Understanding the extent and causes of land degradation is pivotal for effectively prevention and management. This study employs the soil adjusted vegetation index (SAVI), the temperature vegetation dryness index (TVDI), and the salinization detection index (SDI), combined with the analytic hierarchy process and the entropy weight method, to construct a comprehensive land degradation index (LDI). Sen’s slope trend analysis and the Mann-Kendall significance test were used to analyze land degradation trends in the Ebinur Lake watershed from 2002 to 2022. Additionally, the optimal parameters-based geographical detector was used to examine the underlying mechanisms of land degradation. The results indicate the following: (1) From 2002 to 2012, the degree of land degradation in the Ebinur Lake watershed worsened, particularly in the eastern and southeastern parts, as well as in the southern region of Toli County. From 2012 to 2022, land degradation significantly improved, with a notable reduction in degraded land area. (2) Over the period of 2002-2022, 93.08%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$93.08\\%$$\\end{document} of the land in the research region exhibited a declining LDI trend, 3.95%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$3.95\\%$$\\end{document} showed no change, and only 2.96%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2.96\\%$$\\end{document} showed an increasing LDI trend. (3) Moderate, severe, and very severe degradation mainly occurred on grassland and unused land, while light degradation and non-degradation primarily occurred on forest land and cultivated land. (4) Unreasonable land use and overgrazing were identified as the primary factors influencing land degradation, with elevation being a secondary factor. The interaction between land use and other factors was found to be most significant, followed by the synergistic effects of grazing quantity with elevation, annual average temperature, gross domestic product, soil moisture, and elevation with annual average precipitation, and temperature. The results of this study offer an empirical basis and taking decisions assistance for land degradation control in the Ebinur Lake Basin, as well as examples and references for assessing land degradation in other places.

Upaya Mengurangi Resiko Bencana di Pedesaan dengan Memanfaatkan Citra Penginderaan Jauh

The natural disaster is one of the phenomena that can occur at any time, anywhere and anytime. The most common disasters are floods, landslides, tornadoes and earthquakes, which can cause damage, loss of life and even loss of life. The conditions of Tabaroge Village and its surroundings are prone to flooding geographically, geologically, hydrologically and demographically. The condition of the East Luwu Regency area is at the confluence of several earth tectonic plates. Therefore, most of the potential disaster threats are in the Tabaroge Village area and its surroundings. Based on the occurrence of natural disasters in East Luwu Regency in recent years, which occurred in several villages. Judging from the characteristics of the Tabaroge Village area, Efforts to Reduce Disaster Risk in Rural Areas by Utilising Remote Sensing Imagery aims to provide information on locations that have disaster risk. This research uses the analysis methods of Standardised Precipitation Index (SPI), Normalised Difference Vegetation Index (NDVI), Normalised Difference Water Index (NDWI), Soil Adjusted Vegetation Index (SAVI) and Inverse Distance Weighted (IDW) for data exploration using Arcmap (GIS). In future development, it is expected to be able to implement disaster risk reduction by utilising remote sensing imagery in Tabaroge Village, East Luwu Regency.

Analysis of drainage morphometry and spectral indices using earth observation datasets in Palar River basin, India

In this research we analyzed the morphometric parameter of Palar River basin by using the satellite data from open sources for monitoring drainage network. Palar River basin covers 1972.27 sq.km areas with elevation of 226.9 m as highest and 38.01 m lowest above mean sea level. In this research it detected that Palar River basin having 5th order stream with drainage density of 0.40 km/km2 and drainage pattern of dendritic to rectangular. We also draw aspect map, relief map and slope map for the research area by using digital elevation model (DEM) data of 30 m resolution. In this research we also employed spectral indices like normalized difference vegetation index (NDVI), normalized difference water index (NDWI), and soil adjusted vegetation index (SAVI) for the vegetation, water and soil characteristics of the research area. In this research it found that there are major changes in land use/land cover as water bodies and land during these periods of 15 years. Highly positive correlation show between morphometric parameter and spectral indices. In this research groundwater level data for the year 2005 and 2020 are used to validation the study. This research work is very useful in developing solutions for dealing with different types of drought and management of groundwater extraction plans.

Prediction of surface urban heat island based on predicted consequences of urban sprawl using deep learning: A way forward for a sustainable environment

The present work aimed at the spatiotemporal analysis of Land Surface Temperature (LST) and several land-use land-cover spectral indices, namely Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Soil Adjusted Vegetation Index (SAVI), and Modified Normalized Difference Water Index (MNDWI) and to develop a Convolutional Neural Network (CNN) model to predict the LST and the indices for Surface Urban Heat Island (SUHI) evaluation based on the impervious surface area. The predictions were made only for LST and two indices (NDVI and NDBI) because of their strong correlation with LST. Landsat-8 satellite imageries acquired for 2013, 2015, 2017, 2019, and 2021 were utilized, and the Sialkot district, a swiftly urbanizing and advancing industrial city, was selected as a case study area. In the study, first, the indices (NDVI and NDBI) were predicted for 2019, 2021, and 2023 following a sequential procedure, and then based on the predicted indices, the LST for the mentioned years was predicted. Ultimately, to analyze the impact of impervious area on SUHI, impervious and SUHI were extracted for 2019, 2021, and 2023 using the predicted NDBI and LST, respectively, by employing Otsu's Thresholding technique. The predicted LST and indices for 2019 and 2021 were compared with the obtained 2019 and 2021 LST and indices through several statistical measures, such as the kappa index, to evaluate the performance of the CNN model. The kappa index of different kappa statistics for 2019 and 2021 varied between 0.81 and 0.96, which resembles several previous studies, thus indicating sufficient future predictions. SUHI evaluation was conducted based on the observed (2016) and simulated (2021) impervious area and normalized LST images. The results showed that the distribution of the SUHI was highly related to the impervious area. Suppose the urbanization rate in the study area continues at its current pace. In that case, this expansion will cause a dramatic increase in SUHI distribution unless decision-makers consider any proper urban planning model for the study area.

The Use of Remote Sensing Techniques in the Analysis of the Influence of Forest Ecosystems over the Precipitation

The processing of remote sensing images and their integration into a Geographic Information System (GIS) to analyse and manage an area represents a modern approach that is increasingly used. In the present paper, a predominantly moun-tainous area was studied and analysed, located in Hunedoara County – Romania, near the city of Hateg and the Retezat Mountains. A satellite scene from 09.24.2019 from the RapidEye remote sensing system was retrieved, processed and subjected to complex remote sensing analyses. These remote sensing data were analysed and processed, and based on them a series of specific indices were calculated and interpreted, namely, for the characterisation of the vegetation: NDVI (Normalised Difference Vegetation Index), GNDVI (Green Normalized Difference Vegetation Index), NDRE (Normal-ised Difference Red Edge Index), SAVI (Soil Adjusted Vegetation Index), MSAVI (Modified Soil Adjusted Vegetation Index), CI Green (Chlorophyll Index Green), CI Red Edge (Red Edge Chlorophyll Index), RTVI core (Red Edge Tri-angular Vegetation Index), SR (Simple Ratio), Red Edge SR (Red Edge Simple Ratio), LAI (Leaf Area Index).

FLOOD SUSCEPTIBILITY MAPPING USING MACHINE LEARNING IN KENING RIVER, SUB WATERSHED OF BENGAWAN SOLO, TUBAN

Floods are natural occurrences with the potential to cause damage to ecosystems and pose significant threats to human life, resulting in the destruction of property, infrastructure, and socioeconomic challenges. In recent times, flooding in the Sub-Watershed of Bengawan Solo has been linked to the overflowing Kening River in Tuban County. Aim: This study aims to produce a flood susceptibility map to mitigate the frequency of flood occurrences as well as facilitate effective planning for flood disaster risk management. Methodology and results: Flood data is collected from 2016 to 2023 through field surveys, Sentinel-1 satellite imagery, and data from the Development Planning Agency, Tuban County. Integrating remote sensing data from satellite imagery (PlanetScope, Sentinel-2), geographic information systems (GIS), and spatial modeling techniques, a flood susceptibility map is developed for the Kening River catchment. The occurrence of floods in the Kening River area is associated with various factors (11 variables) assessed through the frequency ratio approach, including profil curvature, LS factor, aspect, rainfall, river distance, road distance, building density 100 m, road density 100 m, vegetation type, normalized difference water index (NDWI), and soil adjusted vegetation index (SAVI). The results show flood susceptibility maps utilizing frequency ratio (FR) and convolutional neural network (CNN) techniques. The flood susceptibility map obtained through the CNN method demonstrates a notably high AUC value. The model development generated a validation AUC value of 0.857 for training and 0.856 for testing. Conclusion, significance and impact study: This research provides an understanding into the factors that influence the occurrence of floods in the Kening River catchment area. It also emphasizes the benefit of advanced machine learning approaches in mapping the susceptibility of floods. Furthermore, this study has the potential to be helpful in guiding regional policy decisions and result in enhanced flood risk management measures in Tuban County.

Enhancing the Performance of Machine Learning and Deep Learning-Based Flood Susceptibility Models by Integrating Grey Wolf Optimizer (GWO) Algorithm

Flooding is a recurrent hazard occurring worldwide, resulting in severe losses. The preparation of a flood susceptibility map is a non-structural approach to flood management before its occurrence. With recent advances in artificial intelligence, achieving a high-accuracy model for flood susceptibility mapping (FSM) is challenging. Therefore, in this study, various artificial intelligence approaches have been utilized to achieve optimal accuracy in flood susceptibility modeling to address this challenge. By incorporating the grey wolf optimizer (GWO) metaheuristic algorithm into various models—including recurrent neural networks (RNNs), support vector regression (SVR), and extreme gradient boosting (XGBoost)—the objective of this modeling is to generate flood susceptibility maps and evaluate the variation in model performance. The tropical Manimala River Basin in India, severely battered by flooding in the past, has been selected as the test site. This modeling utilized 15 conditioning factors such as aspect, enhanced built-up and bareness index (EBBI), slope, elevation, geomorphology, normalized difference water index (NDWI), plan curvature, profile curvature, soil adjusted vegetation index (SAVI), stream density, soil texture, stream power index (SPI), terrain ruggedness index (TRI), land use/land cover (LULC) and topographic wetness index (TWI). Thus, six susceptibility maps are produced by applying the RNN, SVR, XGBoost, RNN-GWO, SVR-GWO, and XGBoost-GWO models. All six models exhibited outstanding (AUC above 0.90) performance, and the performance ranks in the following order: RNN-GWO (AUC: 0.968) &gt; XGBoost-GWO (AUC: 0.961) &gt; SVR-GWO (AUC: 0.960) &gt; RNN (AUC: 0.956) &gt; XGBoost (AUC: 0.953) &gt; SVR (AUC: 0.948). It was discovered that the hybrid GWO optimization algorithm improved the performance of three models. The RNN-GWO-based flood susceptibility map shows that 8.05% of the MRB is very susceptible to floods. The modeling found that the SPI, geomorphology, LULC, stream density, and TWI are the top five influential conditioning factors.

Characterisation of Two Vineyards in Mexico Based on Sentinel-2 and Meteorological Data

In Mexico, viticulture represents the second source of employment in the agricultural area after the fruit and vegetable sector. In developed countries, remote sensing is widely used for vineyard monitoring; however, this tool is barely used in the developing countries of Iberoamerica. In this research, our overall objective is to characterise two vineyards in the state of Queretaro (Mexico) using Sentinel-2 and meteorological data, specifically spectral and thermal indices. Results show that spectral indices obtained from Sentinel-2 bands have adequately characterised the phenological dynamics of the different varieties of the vineyards. The Modified Soil-Adjusted Vegetation Index (MSAVI) was adequately used to discriminate between the first stages of vineyards, while the Normalized Difference Vegetation Index (NDVI) was useful for monitoring vineyards during the rest stages of vineyards. Thermal indices have shown that the best grape varieties are those that can adapt to both cooler and warmer temperatures, have a reasonable ripening period, and can produce wines with balanced acidity and flavours. In conclusion, the combination of meteorological (including thermal indices) and remote sensing data (NDVI and MSAVI) provide information for choosing a suitable grape variety for this region.

On-farm cereal rye biomass estimation using machine learning on images from an unmanned aerial system

This study assesses the potential of using multispectral images collected by an unmanned aerial system (UAS) on machine learning (ML) frameworks to estimate cereal rye (Secale cereal L.) biomass. Multispectral images and ground-truth cereal rye biomass data were collected from 15 farmers’ fields up to three times between March and May in northwest Ohio. Images were processed to derive 13 vegetation indices (VIs). Out of 13 VIs, six optimal sets of VIs, including excess green (ExG), normalized green red difference index (NGRDI), soil adjusted vegetation index (SAVI), blue green ratio (B_G_ratio), red-edge triangular vegetation index (RTVI), and normalized difference red-edge (NDRE) were selected using the variance inflation factor (VIF) based feature selection approach. Six regression models including a multiple linear regression (MLR), elastic net (ENET), multivariate adaptive regression splines (MARS), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGB) were investigated for estimation of cereal rye biomass based on the VIs. For most of the models, the six selected VIs performed better than or similar to the full set of 13 VIs with R2 ranging from 0.24 to 0.59 and RMSE ranging from 83.13 to 91.89 g/m2 during 10-fold cross-validation. During independent accuracy assessment with the selected set of VIs, XGB exhibited the highest R2 (0.67) and lowest RMSE (83.13 g/m2) and MAE (48.13 g/m2) followed by RF and ENET. For all the models, the agreement between observed and predicted biomass was high for biomass less than or equal to 200 g/m2 but decreased for biomass greater than 200 g/m2. When field-collected structural features were integrated with the selected VIs, the models showed improved performance, with R2 and RMSE of the models reaching up to 0.82 and 61.67 g/m2 respectively. Among the six VIs, SAVI showed the strongest impact on the model prediction for the best-performing RF and XGB regression models. The findings of this study demonstrate the potential of precisely estimating and mapping cereal rye biomass based on UAS-captured multispectral images. Timely information on cover crop growth can facilitate numerous decision-making processes, including planning the planting operations, and management of nutrients, weeds, and soil moisture to improve agronomic and environmental outcomes.

Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks.

The timely detection of underground natural gas (NG) leaks in pipeline transmission systems presents a promising opportunity for reducing the potential greenhouse gas (GHG) emission. However, existing techniques face notable limitations for prompt detection. This study explores the utility of Vegetation Indicators (VIs) to reflect vegetation health deterioration, thereby representing leak-induced stress. Despite the acknowledged potential of VIs, their sensitivity and separability remain understudied. In this study, we employed ground vegetation as biosensors for detecting methane emissions from underground pipelines. Hyperspectral imaging from vegetation was collected weekly at both plant and leaf scales over two months to facilitate stress detection using VIs and Deep Neural Networks (DNNs). Our findings revealed that plant pigment-related VIs, modified chlorophyll absorption reflectance index (MCARI), exhibit commendable sensitivity but limited separability in discerning stressed grasses. A NG-specialized VI, the optimized soil-adjusted vegetation index (OSAVI), demonstrates higher sensitivity and separability in early detection of methane leaks. Notably, the OSAVI proved capable of discriminating vegetation stress 21 days after methane exposure initiation. DNNs identified the methane leaks following a 3-week methane treatment with an accuracy of 98.2%. DNN results indicated an increase in visible (VIS) and a decrease in near-infrared (NIR) in spectra due to methane exposure.

Drone-based early detection of bark beetle infested spruce trees differs in endemic and epidemic populations

IntroductionEuropean forests face increasing threats due to climate change-induced stressors, which create the perfect conditions for bark beetle outbreaks. The most important spruce forest pest in Europe is the European Spruce Bark Beetle (Ips typographus L.). Effective management of I. typographus outbreaks necessitates the timely detection of recently attacked spruce trees, which is challenging given the difficulty in spotting symptoms on infested tree crowns. Bark beetle population density is one of many factors that can affect infestation rate and symptoms development. This study compares the appearance of early symptoms in endemic and epidemic bark beetle populations using highresolution Unmanned Aerial Vehicles (UAV) multispectral imagery.MethodsIn spring of 2022, host colonization by bark beetles was induced on groups of spruce trees growing in 10 sites in the Southern Alps, characterized by different population density (5 epidemic and 5 endemic). A multispectral sensor mounted on a drone captured images once every 2 weeks, from May to August 2022. The analyses of a set of vegetational indices allowed the actual infested trees’ reflectance features and symptoms appearance to be observed at each site, comparing them with those of unattacked trees.ResultsResults show that high bark beetles population density triggers a more rapid and intense response regarding the emergence of symptoms. Infested trees were detected at least 1 month before symptoms became evident to the human eye (red phase) in epidemic sites, while this was not possible in endemic sites. Key performing vegetation indices included NDVI (Normalized Difference Vegetation Index), SAVI (Soil Adjust Vegetation Index, with a correction factor of 0.44), and NDRE (Normalized Difference Red Edge index).DiscussionThis early-detection approach could allow automatic diagnosis of bark beetles’ infestations and provide useful guidance for the management of areas suffering pest outbreaks.

Longitudinal study of changes in greenness exposure, physical activity and sedentary behavior in the ORISCAV-LUX cohort study

BackgroundGreenness exposure has been associated with many health benefits, for example through the pathway of providing opportunities for physical activity (PA). Beside the limited body of longitudinal research, most studies overlook to what extent different types of greenness exposures may be associated with varying levels of PA and sedentary behavior (SB). In this study, we investigated associations of greenness characterized by density, diversity and vegetation type with self-reported PA and SB over a 9-year period, using data from the ORISCAV-LUX study (2007–2017, n = 628).MethodsThe International Physical Activity Questionnaire (IPAQ) short form was used to collect PA and SB outcomes. PA was expressed as MET-minutes/week and log-transformed, and SB was expressed as sitting time in minutes/day.Geographic Information Systems (ArcGIS Pro, ArcMap) were used to collect the following exposure variables: Tree Cover Density (TCD), Soil-adjusted Vegetation Index (SAVI), and Green Land Use Mix (GLUM). The exposure variables were derived from publicly available sources using remote sensing and cartographic resources. Greenness exposure was calculated within 1000m street network buffers around participants’ exact residential address.ResultsUsing Random Effects Within-Between (REWB) models, we found evidence of negative within-individual associations of TCD with PA (β = − 2.60, 95% CI − 4.75; − 0.44), and negative between-individual associations of GLUM and PA (β = − 2.02, 95% CI − 3.73; − 0.32). There was no evidence for significant associations between greenness exposure and SB. Significant interaction effects by sex were present for the associations between TCD and both PA and SB. Neighborhood socioeconomic status (NSES) did not modify the effect of greenness exposure on PA and SB in the 1000 m buffer.DiscussionOur results showed that the relationship between greenness exposure and PA depended on the type of greenness measure used, which stresses the need for the use of more diverse and complementary greenness measures in future research. Tree vegetation and greenness diversity, and changes therein, appeared to relate to PA, with distinct effects among men and women. Replication studies are needed to confirm the relevance of using different greenness measures to understand its’ different associations with PA and SB.