RESUMEN
Carbon emissions resulting from energy consumption have become a pressing issue for governments worldwide. Accurate estimation of carbon emissions using satellite remote sensing data has become a crucial research problem. Previous studies relied on statistical regression models that failed to capture the complex nonlinear relationships between carbon emissions and characteristic variables. In this study, we propose a machine learning algorithm for carbon emissions, a Bayesian optimized XGboost regression model, using multi-year energy carbon emission data and nighttime lights (NTL) remote sensing data from Shaanxi Province, China. Our results demonstrate that the XGboost algorithm outperforms linear regression and four other machine learning models, with an R2 of 0.906 and RMSE of 5.687. We observe an annual increase in carbon emissions, with high-emission counties primarily concentrated in northern and central Shaanxi Province, displaying a shift from discrete, sporadic points to contiguous, extended spatial distribution. Spatial autocorrelation clustering reveals predominantly high-high and low-low clustering patterns, with economically developed counties showing high-emission clustering and economically relatively backward counties displaying low-emission clustering. Our findings show that the use of NTL data and the XGboost algorithm can estimate and predict carbon emissions more accurately and provide a complementary reference for satellite remote sensing image data to serve carbon emission monitoring and assessment. This research provides an important theoretical basis for formulating practical carbon emission reduction policies and contributes to the development of techniques for accurate carbon emission estimation using remote sensing data.
Asunto(s)
Algoritmos , Monitoreo del Ambiente , Aprendizaje Automático , China , Monitoreo del Ambiente/métodos , Contaminantes Atmosféricos/análisis , Carbono/análisis , Teorema de Bayes , Tecnología de Sensores Remotos , Contaminación del Aire/estadística & datos numéricos , Contaminación del Aire/análisisRESUMEN
Selecting suitable Megacity Solid Waste Disposal (MSWD) sites is a challenging task in densely populated deltas of developing countries, exacerbated by limited public awareness about waste management. One of the major environmental concerns in Dhaka City, the world's densest megacity, is the presence of dumps close to surface water bodies resources. This study employed the Geographic Information System (GIS)-Analytic Hierarchy Process (AHP) framework to integrate geomorphological (slope and flow accumulation), geological (lithological and lineament), hydrogeological (depth to groundwater table and surface waterbody), socioeconomic (Land use land cover, distance to settlement, road, and airport), and climatological (wind direction) determinants, coupled by land-use and hydro-environmental analyses, to map optimal dumps (MSWDO) sites. The resulting preliminary (MSWDP) map revealed 15 potential landfill areas, covering approximately 5237 hectares (ha). Combining statistical analysis of restricted areas (settlements, water bodies, land use) with AHP-based ratings, the MSWDO map revealed two optimal locations (2285 ha). Additionally, the hydro-environmental analysis confirmed the unsuitability of northern sites due to shallow groundwater (< 5.43 m) and thin clay, leaving 11 options excluded. Sites 12 (Zone A, 2255 ha) and 15 (Zone B, 30 ha), with deeper groundwater tables and thicker clay layers, emerged as optimal choices for minimizing environmental risks and ensuring effective long-term waste disposal. This study successfully integrates remote sensing, geospatial data, and GIS-AHP modeling to facilitate the development of sustainable landfill strategies in similar South Asian delta megacities. Such an approach provides valuable insights for policymakers to implement cost-effective and sustainable waste management plans, potentially minimizing the environmental risks to achieve Sustainable Development Goals (SDGs) 6, 11, 13, and 15.
Asunto(s)
Monitoreo del Ambiente , Sistemas de Información Geográfica , Eliminación de Residuos , Bangladesh , Eliminación de Residuos/métodos , Monitoreo del Ambiente/métodos , Instalaciones de Eliminación de Residuos , Tecnología de Sensores Remotos , Residuos Sólidos/análisis , Ciudades , Administración de Residuos/métodosRESUMEN
Real-time assessment of ecological environment quality in arid and semi-arid regions is crucial for the sustainable development of ecological environments in China. In this study, we constructed a topsoil remote sensing ecological index (TRSEI) by coupling five indicators, greenness, wetness, dryness, topsoil grain size, and heat, with the Google Earth Engine (GEE). With the index, we evaluated the ecological environment quality of Wuchuan County from 1990 to 2020, and examined the spatio-temporal variations of ecological environment quality and its driving factors by using univariate linear regression, multiple regression residual analysis, and Hurst index. Results showed that the first principal component of the TRSEI in the study area contributed over 70%, with a mean eigenvalue of 0.148, indicating the effective integration of various ecological indicators by TRSEI. The topsoil grain size index was essential for the assessment of ecological environment quality in arid and semi-arid regions. From 1990 to 2020, the fluctuation range of TRSEI in the study area was between 0.289 and 0.458, showing an overall slight deterioration trend. The ecological environment quality of cropland and de-farming region had improved, with the improved area accounting for 47.9% of the total area. The grassland, barren land, and construction land areas had deteriorated, with the deteriorated area accounting for 52.1% of the total area. In the future, 36.9% of the regions would experience continuous improvement in ecological environment quality, while 41.4% might continue to dete-riorate. Human activities were the primary driving factor for the changes in ecological environment quality in arid and semi-arid regions, accounting for 88.6% of the total area. Climate change also had a significant impact, accounting for 11.4% of the total area. The TRSEI could effectively assess the ecological environment quality of arid and semi-arid regions, providing a scientific basis for ecological conservation and construction in these areas.
Asunto(s)
Clima Desértico , Ecosistema , Monitoreo del Ambiente , Tecnología de Sensores Remotos , China , Tecnología de Sensores Remotos/métodos , Monitoreo del Ambiente/métodos , Conservación de los Recursos Naturales/métodos , Ecología/métodosRESUMEN
Rodent-infested bald spots are crucial indicators of rodent infestation in grasslands. Leveraging Unmanned Aerial Vehicle (UAV) remote sensing technology for discerning detrimental bald spots among plateau pikas has significant implications for assessing associated ecological hazards. Based on UAV-visible light imagery, we classified and recognized the characteristics of plateau pika habitats with five supervised classification algorithms, i.e., minimum distance classification (MinD), maximum likelihood classification (ML), support vector machine classification (SVM), Mahalanobis distance classification (MD), and neural network classification (NN) . The accuracy of the five methods was evaluated using a confusion matrix. Results showed that NN and SVM exhibited superior performance than other methods in identifying and classifying features indicative of plateau pika habitats. The mapping accuracy of NN for grassland and bald spots was 98.1% and 98.5%, respectively, with corresponding user accuracy was 98.8% and 97.7%. The overall model accuracy was 98.3%, with a Kappa coefficient of 0.97, reflecting minimal misclassification and omission errors. Through practical verification, NN exhibited good stability. In conclusion, the neural network method was suitable for identifying rodent-damaged bald spots within alpine meadows.
Asunto(s)
Algoritmos , Ecosistema , Pradera , Tecnología de Sensores Remotos , Roedores , Dispositivos Aéreos No Tripulados , Animales , Tecnología de Sensores Remotos/métodos , Lagomorpha , Redes Neurales de la Computación , Monitoreo del Ambiente/métodos , Máquina de Vectores de Soporte , ChinaRESUMEN
Exploring the temporal and spatial dynamics of vegetation coverage in the Heilongjiang Basin and its response to climate change can provide a theoretical basis and data support for integrated basin management for three countries (Mongolia, China and Russia) in the region. We used MOD13Q1 remote sensing data from Google Earth Engine (GEE) platform between 2000 and 2020 to process the normalized vegetation index (NDVI) through the maximum value composites method, and calculated the vegetation coverage (FVC) using the dimidiate pixel model. The Sen+MK trend analysis method was employed to monitor the dynamics of FVC, while the Pearson correlation coefficient was utilized to quantify the responses of FVC to climate change. The results showed that the overall FVC in the Heilongjiang Basin exhibited a slight decreasing trend during 2000-2020, with an annual rate of 0.1%. The FVC in Mongolia showed a fluctuating increase trend (0.13%), while slight decrease trends were observed for Russia (0.15%) and China (0.08%). The FVC predominantly slightly degraded and severely degraded, accounting for 34% and 17% of the area, respectively, while the significantly improved area only accounted for 9%. The impact of precipitation on FVC in the study area was significantly greater than that of temperature. The proportion of areas where precipitation and temperature had a significant impact on FVC was 8.2% and 2.2%, respectively. The correlation coefficient between precipitation and FVC was the highest in Mongolia (r=0.446, P<0.05), and the lowest in Russian region (r=-0.442, P< 0.05).
Asunto(s)
Cambio Climático , Ecosistema , Monitoreo del Ambiente , China , Monitoreo del Ambiente/métodos , Análisis Espacio-Temporal , Tecnología de Sensores Remotos , Ríos , Conservación de los Recursos Naturales , Mongolia , Imágenes SatelitalesRESUMEN
Monitoring the land use/land cover (LU/LC) changes that have occurred with rapid population growth and urbanization since the Industrial Revolution is important for the optimal configuration of landscape patterns and ensuring the sustainability of ecological functions. Spatiotemporal dynamic pattern of LU/LC change using high-resolution land use data is an indicator to evaluate the landscape ecological risk through landscape pattern index analysis. In this study, the landscape ecological risk index (LERi) based on LU/LC change was calculated using remote sensing images of Landsat TM (Thematic Mapper) and OLI (Operational Land Imager) Rdata of a Gediz Mainstream Sub-basin in Turkiye between 1992 and 2022, and the spatial distribution regularity of LERi values was determined with spatial statistical analysis. According to the results, it was determined that the LERi values of the study area changed by 45% in 30 years. The highest change is in the very high-risk class, with an increase of 10.96%, and the least change occurred in the very low-risk class, with a decrease of 1.29%. According to the obtained statistical analysis results, it was determined that the global spatial autocorrelation values analyzed at different grain levels showed positive autocorrelation for both years and that the LERi values tended to have strong spatial clustering. As a result, it is emphasized that strict control measures should be taken for areas showing High-High (HH) autocorrelation type located in the southeast and north-southwest line of the study area at the local level, and ecological restoration applications should be given priority in these areas.
Asunto(s)
Monitoreo del Ambiente , Análisis Espacio-Temporal , Monitoreo del Ambiente/métodos , Turquía , Conservación de los Recursos Naturales , Urbanización , Ecosistema , Medición de Riesgo , Imágenes Satelitales , Ecología , Tecnología de Sensores RemotosRESUMEN
Heavy mineral deposits occur in several coastal areas of the world, formed over a long period due to variations in mean sea level, wave action, and winds. These are the main sources of ilmenite (FeTiO3), which in turn is the source of more than 80% of the TiO2 produced and applied in various industries, most recently in nanotechnology. The present study mapped heavy mineral deposits on the coast of Rio Grande do Sul in southern Brazil using integrated proximal and orbital thermal infrared (TIR) remote sensing techniques. Mineral groups, such as oxides and silicates, have spectral features in the TIR wavelengths. Using laboratory spectroscopy at TIR using Nicolet 6700 Thermo Scientific Spectrometer, we measured the spectral signature of the local sample of heavy minerals (between 8 and 14 µm) and identified a diagnostic spectral feature at 10.75 µm. The signature was resampled to be compatible with the Advanced Spaceborne Thermal Emission Radiometer (ASTER) sensor bandwidth values and used as a reference endmember for the Spectral Angle Mapper (SAM) and Linear Spectral Unmixing (LSU) digital image classification algorithms. Thus, we identified the presence of the reference endmember (heavy minerals) in the pixels of the ASTER scene. In pixels classified by SAM as the presence of heavy minerals, LSU was applied to estimate the surface concentration within the pixel. The results showed a concentration of up to 20% of heavy minerals, with the highest concentration on the beach and dune fields. Opaque minerals such as ilmenite do not have spectral reflectance features in visible, near-infrared, and short-wave infrared, which makes their identification by remote sensing difficult. The present study showed that the integration of proximal and orbital as well as hyperspectral and multispectral thermal data can be considered as an alternative for detecting and mapping heavy minerals in coastal areas.
Asunto(s)
Minerales , Tecnología de Sensores Remotos , Brasil , Minerales/análisis , Tecnología de Sensores Remotos/métodos , Monitoreo del Ambiente/métodos , Titanio/análisis , Titanio/químicaRESUMEN
The U-Chang-Shi (Urumqi-Changji-Shihezi) urban cluster, located at the heart of Xinjiang, boasts abundant natural resources. Over the past two decades, rapid urbanization, industrialization, and climate change have significantly threatened the region's ecological livability. To comprehensively, scientifically, and objectively assess the ecological livability of this area, this study leverages the Google Earth Engine (GEE) platform and multi-source remote sensing data to develop a comprehensive evaluation metric: the Remote Sensing Ecological Livability Index (RSELI). This aims to examine the changes in the ecological livability of the U-Chang-Shi urban cluster from 2000 to 2020. The findings show that despite some annual improvements, the overall trend in ecological livability is declining, indicating that the swift pace of urbanization and industrialization has placed considerable pressure on the region's ecological environment. Land use changes, driven by urban expansion and the growth in agricultural and industrial lands, have progressively encroached upon existing green spaces and water bodies, further deteriorating the ecological environment. Additionally, the region's topographical features have influenced its ecological livability; large terrain fluctuations have made soil erosion and geological disasters common. Despite the central plains' vast rivers providing ample water resources, over exploitation and ill-conceived hydrological constructions have led to escalating water scarcity. The area near the Gurbantunggut Desert in the north, with its extremely fragile ecological environment, has long been unsuitable for habitation. This study provides a crucial scientific basis for the future development of the U-Chang-Shi urban cluster and hopes to offer theoretical support and practical guidance for the sustainable development and ecological improvement of the region.
Asunto(s)
Conservación de los Recursos Naturales , Tecnología de Sensores Remotos , Urbanización , China , Tecnología de Sensores Remotos/métodos , Monitoreo del Ambiente/métodos , Ciudades , Humanos , Cambio ClimáticoRESUMEN
Drought is one of the common natural disasters with a wide range of occurrences in terms of space and time, and with varying levels of severity, that may result in economic damage and health issues to humans. This study focuses on assessing drought severity in the Central Highlands of Vietnam based on ground meteorological stations and multispectral remote sensing data. A Modification of the Normalized Difference Drought Index (MNDDI) was developed to enhance the effectiveness of remote sensing indices in the drought assessment. Results indicate that MNDDI outperforms Normalized Difference Drought Index and other investigated indicators, such as Normalized Difference Vegetation Index, Normalized Difference Latent Heat Index, and Normalized Difference Water Index, in representing the Earth's surface response to drought events. Correlations ranging from 0.85 to 0.63 were identified between MNDDI and various time scales of the commonly used meteorological drought indicator, namely the Standardized Precipitation Index, during the drought year of 2015. This work also reveals the superiority of MNDDI in portraying the response of land cover types to drought situations. The finding of a severe drought phenomenon in critical agricultural zones is highly consistent with the report from the Ministry of Agriculture and Rural Development of Vietnam. This study contributes valuable insights to the preliminary assessment of drought through remote sensing data, offering a foundation for precise drought outlooks and effective risk management strategies.
Asunto(s)
Sequías , Monitoreo del Ambiente , Tecnología de Sensores Remotos , Vietnam , Monitoreo del Ambiente/métodos , Imágenes Satelitales , Agricultura/métodosRESUMEN
Groundwater depletion and water scarcity are pressing issues in water-limited regions worldwide, including Pakistan, where it ranks as the third-largest user of groundwater. Lahore, Pakistan, grapples with severe groundwater depletion due to factors like population growth and increased agricultural land use. This study aims to address the lack of comprehensive groundwater availability data in Lahore's semi-arid region by employing GIS techniques and remote sensing data. Various parameters, including Land Use and Land Cover (LULC), Rainfall, Drainage Density (DD), Water Depth, Soil Type, Slope, Population Density, Road Density, Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-Up Index (NDBI), Moisture Stress Index (MSI), Water Vegetation Water Index (WVWI), and Land Surface Temperature (LST), are considered. Thematic layers of these parameters are assigned different weights based on previous literature, reclassified, and superimposed in weighted overlay tool to develop a groundwater potential zones index map for Lahore. The groundwater recharge potential zones are categorized into five classes: Extremely Bad, Bad, Mediocre, Good, and Extremely Good. The groundwater potential zone index (GWPZI) map of Lahore reveals that the majority falls within the Bad to Mediocre recharge potential zones, covering 33% and 28% of the total land area in Lahore, respectively. Additionally, 14% of the total area falls under the category of Extremely Bad recharge potential zones, while Good to Extremely Good areas cover 19% and 6%, respectively. By providing policymakers and water supply authorities with valuable insights, this study underscores the significance of GIS techniques in groundwater management. Implementing the findings can aid in addressing Lahore's groundwater challenges and formulating sustainable water management strategies for the city's future.
Asunto(s)
Monitoreo del Ambiente , Sistemas de Información Geográfica , Agua Subterránea , Tecnología de Sensores Remotos , Pakistán , Agua Subterránea/química , Monitoreo del Ambiente/métodos , Abastecimiento de Agua/estadística & datos numéricos , Agricultura/métodosRESUMEN
The rapid reduction of forests due to environmental impacts such as deforestation, global warming, natural disasters such as forest fires as well as various human activities is an escalating concern. The increasing frequency and severity of forest fires are causing significant harm to the ecosystem, economy, wildlife, and human safety. During dry and hot seasons, the likelihood of forest fires also increases. It is crucial to accurately monitor and analyze the large-scale changes in the forest cover to ensure sustainable forest management. Remote sensing technology helps to precisely study such changes in forest cover over a wide area over time. This research analyzes the impact of forest fires over time, identifies hotspots, and explores the environmental factors that affect forest cover change. Sentinel-2 imagery was utilized to study changes in Brunei Darussalam's forest cover area over five years from 2017 to 2022. An object-based approach, Simple Non-Iterative Clustering (SNIC), is employed to cluster the region using NDVI values and analyze the changes per cluster. The results indicate that the area of the clusters reduced where fire incidence occurred as well as the precipitation dropped. Between 2017 and 2022, the increased forest fires and decreased precipitation levels resulted in the change in cluster areas as follows: 66.11%, 69.46%, 68.32%, 73.88%, 77.27%, and 78.70%, respectively. Additionally, hotspots in response to forest fires each year were identified in the Belait district. This study will help forest managers assess the causes of forest cover loss and develop conservation and afforestation strategies.
Asunto(s)
Conservación de los Recursos Naturales , Monitoreo del Ambiente , Bosques , Incendios Forestales , Monitoreo del Ambiente/métodos , Conservación de los Recursos Naturales/métodos , Ecosistema , Tecnología de Sensores Remotos , Incendios , ÁrbolesRESUMEN
One reason arid and semi-arid environments have been used to store waste is due to low groundwater recharge, presumably limiting the potential for meteoric water to mobilize and transport contaminants into groundwater. The U.S. Department of Energy Office of Legacy Management (LM) is evaluating selected uranium mill tailings disposal cell covers to be managed as evapotranspiration (ET) covers, where vegetation is used to naturally remove water from the cover profile via transpiration, further reducing deep percolation. An important parameter in monitoring the performance of ET covers is soil moisture (SM). If SM is too high, water may drain into tailings material, potentially transporting contaminants into groundwater; if SM is too low, radon flux may increase through the cover. However, monitoring SM via traditional instrumentation is invasive, expensive, and may fail to account for spatial heterogeneity, especially over vegetated disposal cells. Here we investigated the potential for non-invasive SM monitoring using radar remote sensing and other geospatial data to see if this approach could provide a practical, accurate, and spatially comprehensive tool to monitor SM. We used theoretical simulations to analyze the sensitivity of multi-frequency radar backscatter to SM at different depths of a field-scale (3 ha) drainage lysimeter embedded within an in-service LM disposal cell. We then evaluated a shallow and deep form of machine learning (ML) using Google Earth Engine to integrate multi-source observations and estimate the SM profile across six soil layers from depths of 0-2 m. The ML models were trained using in situ SM measurements from 2019 and validated using data from 2014 to 2018 and 2020-2021. Model predictors included backscatter observations from satellite synthetic aperture radar, vegetation, temperature products from optical infrared sensors, and accumulated, gridded rainfall data. The radar simulations confirmed that the lower frequencies (L- and P-band) and smaller incidence angles show better sensitivity to deeper soil layers and an overall larger SM dynamic range relative to the higher frequencies (C- and X-band). The ML models produced accurate SM estimates throughout the soil profile (r values from 0.75 to 0.94; RMSE = 0.003-0.017 cm3/cm3; bias = 0.00 cm3/cm3), with the simpler shallow-learning approach outperforming a selected deep-learning model. The ML models we developed provide an accurate, cost-effective tool for monitoring SM within ET covers that could be applied to other vegetated disposal cell covers, potentially including those with rock-armored covers.
Asunto(s)
Aprendizaje Automático , Tecnología de Sensores Remotos , Suelo , Uranio , Uranio/análisis , Suelo/química , Agua Subterránea/química , Monitoreo del Ambiente/métodosRESUMEN
Using satellite remote sensing, we show the distribution, dominant type, and amounts of marine debris off the northeast coast of Japan after the Great East Japan Earthquake on 11 March 2011 and subsequent tsunami. Extensive marine debris was found on March 12, with the maximal amount found on March 13. The debris was found to be mainly wood (possibly lumber wood), with an estimated 1.5 million metric tons in an elongated water area of 6800 km2 (18 km E-W and 380 km N-S) near parallel to the coast between 36.75°N and 40.25°N. The amount decreased rapidly with time, with scattered debris patches captured in high-resolution satellite images up to April 6. These results provide new insights on the initial distribution of the Japanese Tsunami Marine Debris, which may be used to help find bottom deposition of debris and help refine numerical models to predict the debris trajectory and fate. SYNOPSIS: Marine debris induced by the 2011 Great East Japan Earthquake and Tsunami is found to be mainly composed of wood and possibly lumber wood from constructions, with maximum amount on 13 March 2011 distributed within a narrow band of â¼18 km near parallel to the northeast coast of Japan between 36.75°N and 40.25°N.
Asunto(s)
Terremotos , Monitoreo del Ambiente , Tecnología de Sensores Remotos , Tsunamis , Japón , Monitoreo del Ambiente/métodos , Residuos/análisis , MaderaRESUMEN
Marine plastic pollution poses significant ecological, economic, and social challenges, necessitating innovative detection, management, and mitigation solutions. Spectral imaging and optical remote sensing have proven valuable tools in detecting and characterizing macroplastics in aquatic environments. Despite numerous studies focusing on bands of interest in the shortwave infrared spectrum, the high cost of sensors in this range makes it difficult to mass-produce them for long-term and large-scale applications. Therefore, we present the assessment and transfer of various machine learning models across four datasets to identify the key bands for detecting and classifying the most prevalent plastics in the marine environment within the visible and near-infrared (VNIR) range. Our study uses four different databases ranging from virgin plastics under laboratory conditions to weather plastics under field conditions. We used Sequential Feature Selection (SFS) and Random Forest (RF) models for the optimal band selection. The significance of homogeneous backgrounds for accurate detection is highlighted by a 97 % accuracy, and successful band transfers between datasets (87 %-91 %) suggest the feasibility of a sensor applicable across various scenarios. However, the model transfer requires further training for each specific dataset to achieve optimal accuracy. The results underscore the potential for broader application with continued refinement and expanded training datasets. Our findings provide valuable information for developing compelling and affordable detection sensors to address plastic pollution in coastal areas. This work paves the way towards enhancing the accuracy of marine litter detection and reduction globally, contributing to a sustainable future for our oceans.
Asunto(s)
Monitoreo del Ambiente , Aprendizaje Automático , Plásticos , Plásticos/análisis , Monitoreo del Ambiente/métodos , Contaminantes Químicos del Agua/análisis , Tecnología de Sensores RemotosRESUMEN
Maize is a crop of global economic importance and is widely cultivated throughout the Brazilian territory. The use of biostimulants can increase yield and improve crop yield. Unmanned aerial vehicles can be employed in arable areas, allowing their use in an economically way. This study to evaluate the use of biostimulant and the best application timing using photogrammetric indexes in maize, and indicate the most suitable plant index for yield increase through a Pearson's correlation. The DJI Drone coupled with RGB camera was used, and the images were processed through the AgisoftPhotoscan® software to generate the orthomosaic, and the QGIS® software version 3.4.15 with GRASS was used to generate thematic maps with the classification of the indexes of vegetation (NGRDI, EXG, SAVI, TGI, GLI, RI). A matrix of Pearson correlation coefficients between the variables was also created, and the results were analyzed with the R software. In general, the products Pyroligneous Extract (PE) and the hormonal product (HP) were the best for the two seasons studied. However, the HP was the best product to mitigate plant water stress in the dry period. Application at phenological stage V3 showed the lowest growth in the rainy season and in application to the seeds in the dry season. Dose 4 of the pyroligneous extract increased productivity in the rainy season and level 3.4 for the hormone product. Among the indexes evaluated, only the SAVI index showed significant differences between the others and showed significance for productivity in the two periods.
Asunto(s)
Tecnología de Sensores Remotos , Estaciones del Año , Zea mays , Zea mays/crecimiento & desarrollo , Reguladores del Crecimiento de las Plantas/farmacologíaRESUMEN
Anthropogenic habitat destruction and climate change are reshaping the geographic distribution of plants worldwide. However, we are still unable to map species shifts at high spatial, temporal, and taxonomic resolution. Here, we develop a deep learning model trained using remote sensing images from California paired with half a million citizen science observations that can map the distribution of over 2,000 plant species. Our model-Deepbiosphere-not only outperforms many common species distribution modeling approaches (AUC 0.95 vs. 0.88) but can map species at up to a few meters resolution and finely delineate plant communities with high accuracy, including the pristine and clear-cut forests of Redwood National Park. These fine-scale predictions can further be used to map the intensity of habitat fragmentation and sharp ecosystem transitions across human-altered landscapes. In addition, from frequent collections of remote sensing data, Deepbiosphere can detect the rapid effects of severe wildfire on plant community composition across a 2-y time period. These findings demonstrate that integrating public earth observations and citizen science with deep learning can pave the way toward automated systems for monitoring biodiversity change in real-time worldwide.
Asunto(s)
Ciencia Ciudadana , Aprendizaje Profundo , Ecosistema , Plantas , Tecnología de Sensores Remotos , Tecnología de Sensores Remotos/métodos , Ciencia Ciudadana/métodos , Plantas/clasificación , Cambio Climático , Bosques , Biodiversidad , California , Incendios Forestales , Humanos , Conservación de los Recursos Naturales/métodosRESUMEN
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.
Asunto(s)
Cianobacterias , Monitoreo del Ambiente , Eutrofización , Lagos , Tecnología de Sensores Remotos , Cianobacterias/crecimiento & desarrollo , Monitoreo del Ambiente/métodos , Lagos/microbiología , China , Modelos LinealesRESUMEN
Assessing drought impacts is necessary for pursuing sustainable development goals relevant to food security and land degradation. Data availability is a major restriction and remote sensing has been promoted for this purpose. Version 3 of WaPOR has been released in 2023, which provides global coverage of remote sensing-derived water productivity indicators and could allow improved analysis of drought impacts, but validation is still needed. This study explores the utility of remote sensing-derived productivity data from WaPOR as a proxy indicator for agricultural drought impacts. The analysis utilized (1) production surveys, (2) meteorological measurements for drought analysis, and (3) remote sensing-derived gross and net biomass water productivities (GBWP & NBWP) and total biomass production (TBP). All layers were analyzed against the Standardized Precipitation and Standardized Precipitation Evapotranspiration Indices (SPI and SPEI) over drought-vulnerable locations in Irbid and Madaba governorates in Jordan. Strong and significant correlations (R2 0.5-0.8, P < 0.05) were obtained between drought intensities and GBWP and NBWP layers, particularly in the May-Sep periods. These correlations were higher than previously tested remotely sensed indicators for agricultural drought impacts. Water productivity and biomass production averages were lower during drier periods and higher during wet periods, but pairwise testing did not reveal significant differences. There is sufficient evidence that WaPOR data demonstrates behavior that reflects agricultural response to drought, and further assessment in other agroclimatic zones is recommended. This could potentially allow for enhanced evaluation of management strategies, decision support, and policy recommendations for drought mitigation.
Asunto(s)
Agricultura , Biomasa , Sequías , Monitoreo del Ambiente , Tecnología de Sensores Remotos , Agricultura/métodos , Monitoreo del Ambiente/métodos , Lluvia , JordaniaRESUMEN
Eucalyptus species play an important role in the global carbon cycle, especially in reducing the greenhouse effect as well as storing atmospheric CO2. Thus, assessing the amount of CO2 released by the soil in forest areas can generate important information for environmental monitoring. This study aims to verify the relation between soil carbon dioxide (CO2) flux (FCO2), spectral bands, and vegetation indices (VIs) derived from a UAV-based multispectral camera over an area of eucalyptus species. Multispectral imageries (green, red-edge, and near-infrared) from the Parrot Sequoia sensor, derived vegetation indices, and the FCO2 data from a LI-COR 8100 analyzer, combined with soil moisture and temperature data, were collected and related. The vegetation indices ATSAVI (Adjusted Transformed Soil-Adjusted VI), GSAVI (Green Soil Adjusted Vegetation Index), and SAVI (Soil-Adjusted Vegetation Index), which use soil correction factors, exhibited a strong negative correlation with FCO2 for the species E. camaldulensis, E. saligna, and E. urophylla species. A Multivariate Analysis of Variance showed significance (p < 0.01) for the species factor, which indicates that there are differences when considering all variables simultaneously. The results achieved in this study show a specific correlation between the data of soil CO2 emission and the eucalypt species, providing a distinction of values between the species in the statistical data.
Asunto(s)
Dióxido de Carbono , Eucalyptus , Suelo , Eucalyptus/química , Dióxido de Carbono/análisis , Suelo/química , Monitoreo del Ambiente/métodos , Tecnología de Sensores Remotos/métodos , BosquesRESUMEN
Using satellite RS data predicting mangrove vegetation carbon stock (MVC) is the popular and efficient approach at a large scale to protect mangroves and promote carbon trading. Satellite data have performed poorly in predicting MVC due to saturation issues. UAV-LiDAR data overcomes these limitations by providing detailed structural vegetation information. However, how to cross-scale integration of UAV-LiDAR and satellite RS data and the selection of features and machine learning methods hampered the practitioner in making a lightweight but efficient model to predict the MVC. Our study integrated UAV-LiDAR, Sentinel-1, and Sentinel-2 to extract spectral, structural, and textural features at the regional scale. We estimated the influences of different combinations between three vegetation features and machine learning methods (Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Regression Tree (GBDT), and Extreme Gradient Regression Tree (XGBOOST)) on the results of MVC prediction, and constructed a framework for estimating mangrove vegetation aboveground (ACG) and belowground (BCG) carbon storage in Zhanjiang, the largest mangrove area of China. Our research shows: 1) Compared to using satellite remote sensing (RS), integrating UAV and satellite RS data and fusing multiple vegetation features significantly improved the accuracy of mangrove vegetation carbon stock (MVC) predictions. 2) Structural features, particularly canopy height retrieved from UAV and satellite RS, are essential indicators for predicting MVC. Combined with spectral and structural features, regional MVC was precisely predicted. 3)Although the influence of different machine learning methods on MVC prediction was not significant, XGBOOST demonstrated relatively high precision. We recommend that mangrove practitioners integrate UAV and satellite RS data to predict MVC at a regional scale. Importantly, governments should prioritize the application of UAV-LiDAR in forestry monitoring and establish a long-term mangrove monitoring database to aid in estimating blue carbon resources and promoting blue carbon trading.