Environmental Monitoring and Assessment, Journal Year: 2025, Volume and Issue: 197(2)
Published: Jan. 10, 2025
Language: Английский
Agronomy, Journal Year: 2025, Volume and Issue: 15(3), P. 676 - 676
Published: March 11, 2025
Heavy metal pollution of farmland is worsened by the excessive introduction heavy elements into soil systems, posing a substantial threat for global food security and human health. The traditional laboratory-based methods monitoring metals are limited large-scale applications, while hyperspectral imagery data-based still face accuracy challenges. Therefore, fusion XGBoost model based on superposition ensemble learning packaging proposed with high using imagery. We took Xiong’an New Area, Hebei Province, as study area, acquired content chemical analysis. XGB-Boruta-PCC algorithm was used precise feature selection to obtain final modeled spectral response features. On this basis, performance indicators Optuna-optimized were compared linear nonlinear models. optimal extended entire region drawing spatial distribution map content. results suggested that method effectively achieved double dimensionality reduction high-dimensional data, extracting features contribution, which, combined model, exhibited greater general estimation accuracies (Pb) in (i.e., Pb: R2 = 0.82, RMSE 11.58, MAE 9.89). mapping indicated there exceedances southwest parts west over research region. Factories activities potential causes Pb contamination farmland. In conclusion, innovative can quickly accurately achieve farmland, ZY-1-02E spaceborne proving be reliable tool
Language: Английский
Citations
1
Remote Sensing, Journal Year: 2022, Volume and Issue: 14(7), P. 1581 - 1581
Published: March 25, 2022
Satellite-estimated solar-induced chlorophyll fluorescence (SIF) is proven to be an effective indicator for dynamic drought monitoring, while the capability of SIF assess variability dryland vegetation under water and heat stress remains challenging. This study presents analysis responses worst extreme over past two decades in Australia, using multi-source spaceborne derived from Global Ozone Monitoring Experiment-2 (GOME-2) TROPOspheric Instrument (TROPOMI). Vegetation functioning was substantially constrained by this event, especially interior which there hardly seasonal growth detected neither satellite-based observations nor tower-based flux measurements. At a 16-day interval, both enhanced index (EVI) can timely capture reduction at onset ecosystems. The results demonstrate that satellite-observed has potential characterizing monitoring spatiotemporal dynamics water-limited ecosystems, despite coarse spatial resolution coupled with high-retrieval noise as compared EVI. Furthermore, our highlights retrieved TROPOMI featuring promising accurately tracking drought-induced variation heterogeneous vegetation.
Language: Английский
Citations
30
Remote Sensing, Journal Year: 2022, Volume and Issue: 14(13), P. 2985 - 2985
Published: June 22, 2022
Accurate characterization of spatial patterns and temporal variations in dryland vegetation is great importance for improving our understanding terrestrial ecosystem functioning under changing climates. Here, we explored the spatiotemporal variability phenology using satellite-observed Solar-Induced chlorophyll Fluorescence (SIF) Enhanced Vegetation Index (EVI) along North Australian Tropical Transect (NATT). Substantial impacts extreme drought intense wetness on productivity are observed by both SIF EVI, especially arid/semiarid interior Australia without detectable seasonality dry year 2018–2019. The greenness-based index can more accurately capture seasonal interannual variation production than (EVI r2: 0.47~0.86, 0.47~0.78). However, during brown-down periods, rate decline EVI evidently slower that situ measurement gross primary (GPP), due partially to advanced absorbed photosynthetically active radiation. Over 70% (except Hummock grasslands) 40% shrublands) be explained water-related drivers (rainfall soil moisture). By contrast, air temperature contributed 25~40% effective fluorescence yield (SIFyield) across all biomes. In spite high retrieval noises variable accuracy phenological metrics (MAE: 8~60 days), spaceborne observations, offsetting drawbacks products with a potentially lagged end season, have promising capability mapping characterizing dynamics phenology.
Language: Английский
Citations
29
Remote Sensing, Journal Year: 2023, Volume and Issue: 15(4), P. 1066 - 1066
Published: Feb. 15, 2023
One reason for soil degradation is salinization in inland dryland, which poses a substantial threat to arable land productivity. Remote-sensing technology provides rapid and accurate assessment salinity monitoring, but there lack of high-resolution remote-sensing spatial estimations. The PlanetScope satellite array high-precision mapping surface monitoring through its 3-m resolution near-daily revisiting frequency. This study’s use the new attempt estimate drylands. We hypothesized that field observations, data, spectral indices derived from data using partial least-squares regression (PLSR) method would produce reasonably regional maps based on 84 ground-truth various parameters, like band reflectance, published indices. results showed newly constructed red-edge yellow indices, we were able develop several inversion models maps. Different algorithms, including Boruta feature preference, Random Forest algorithm (RF), Extreme Gradient Boosting (XGBoost), applied variable selection. (YRNDSI YRNDVI) had best Pearson correlations 0.78 −0.78. also found proportions bands accounted large proportion essential strategies three with preference at 80%, RF XGBoost 60%, indicating these two contributed more estimation results. PLSR model different XGBoost-PLSR coefficient determination (R2), root mean square error (RMSE), ratio performance deviation (RPD) values 0.832, 12.050, 2.442, respectively. These suggest has potential significantly advance research by providing wealth fine-scale information.
Language: Английский
Citations
20
Soil and Tillage Research, Journal Year: 2024, Volume and Issue: 244, P. 106247 - 106247
Published: Aug. 6, 2024
Language: Английский
Citations
7
Environmental Geochemistry and Health, Journal Year: 2022, Volume and Issue: 44(11), P. 3765 - 3777
Published: Jan. 17, 2022
Language: Английский
Citations
28
Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy, Journal Year: 2022, Volume and Issue: 275, P. 121190 - 121190
Published: March 25, 2022
Language: Английский
Citations
28
Remote Sensing, Journal Year: 2022, Volume and Issue: 14(3), P. 472 - 472
Published: Jan. 19, 2022
This study tested and evaluated a suite of nine individual base learners seven model averaging techniques for predicting the spatial distribution soil properties in central Iran. Based on nested-cross validation approach, results showed that artificial neural network Random Forest were most effective organic matter electrical conductivity, respectively. However, all performed better than learners. For example, Granger–Ramanathan approach resulted highest prediction accuracy matter, while Bayesian was sand content. These indicate approaches could improve predictive properties. The resulting maps, produced at 30 m resolution, can be used as valuable baseline information managing environmental resources more effectively.
Language: Английский
Citations
25
Emerging contaminants, Journal Year: 2023, Volume and Issue: 9(1), P. 100204 - 100204
Published: Jan. 6, 2023
Aquatic environment gets highly polluted due to the presence of heavy metals, which are usually discharged into water bodies because rapid industrialization. The main purpose this study is evaluate effects chromium toxicity on histo-biochemical biomarkers Labeo rohita. A total 240 randomly selected fish were distributed four aquaria (n = 20). Three groups designated as T1, T2 and T3 exposed with 1/3rd, 1/5th 1/10th LC50 chloride, fourth group was chromium-free control (T0). Results showed a significant (p < 0.05) decrease in blood parameters such hematocrit, red cells, hemoglobin, mean cell hemoglobin platelets. In contrast, volume white values increased significantly. results obtained by comet assay that DNA damage significantly chromium-exposed compared control. At histopathological level, observed alterations gill tissues degeneration epithelium, fusion secondary lamellae, lamellar curling, hypertrophy, telangiectasis oedema, while liver necrosis, dilation vein, congestion vessels, hepatocytes degeneration, melano-macrophage centers, pigmentation hemorrhage. kidney, histological glomerular destruction, damaged oedema seen. Those suggest has ability bring variations integrity, histopathology
Language: Английский
Citations
14
Remote Sensing, Journal Year: 2021, Volume and Issue: 13(22), P. 4643 - 4643
Published: Nov. 18, 2021
Controlling and managing surface source pollution depends on the rapid monitoring of total nitrogen in water. However, complex factors affecting water quality (plant shading suspended matter water) make direct estimation extremely challenging. Considering spectral response mechanisms emergent plants, we coupled discrete wavelet transform (DWT) fractional order discretization (FOD) techniques with three machine learning models (random forest (RF), bagging algorithm (bagging), eXtreme Gradient Boosting (XGBoost)) to mine this potential information. A 567 were developed, airborne hyperspectral data processed various DWT scales FOD compared. The effective information reflectance better emphasized after processing. After processing original spectrum (OR), its sensitivity TN was maximally improved by 0.22, correlation between optimally increased 0.57. transformed enhanced model accuracy, especially for DWT. For RF, 82% R2 values 0.02~0.72 compared using spectra; 78.8% 0.01~0.53 65.0% XGBoost 0.01~0.64. grey relation analysis (GRA) yielded best highest precision = 0.91 L6. In conclusion, appropriately scaled can substantially improve accuracy extracting from UAV images. These outcomes may facilitate further development accurate sophisticated global waters drone or satellite data.
Language: Английский
Citations
30