A Machine Learning Approach for Mapping Chlorophyll Fluorescence at Inland Wetlands

Remote Sensing, Journal Year: 2023, Volume and Issue: 15(9), P. 2392 - 2392

Published: May 3, 2023

Wetlands are a critical component of the landscape for climate mitigation, adaptation, biodiversity, and human health prosperity. Keeping an eye on wetland vegetation is crucial due to it playing major role in planet’s carbon cycle ecosystem management. By measuring chlorophyll fluorescence (ChF) emitted by plants, we can get precise understanding current state photosynthetic activity. In this study, applied Extreme Gradient Boost (XGBoost) algorithm map ChF Biebrza Valley, which has unique Europe peatlands, as well highly diversified flora fauna. Our results revealed advantages using set classifiers derived from EO Sentinel-2 (S-2) satellite image mosaics accurately spatio-temporal distribution terrestrial landscape. The validation proved that XGBoost quite accurate estimating with good determination 0.71 least bias 0.012. precision measurements reliant upon determining optimal S-2 overpass time, influenced developmental stage plants at various points during growing season. Finally, model performance indicated biophysical factors characterized greenness- leaf-pigment-related spectral indices. However, utilizing indices based extended periods remote sensing data better capture land phenology features improve accuracy mapping fluorescence.

Language: Английский

---

Remote sensing retrieval of inland water quality parameters using Sentinel-2 and multiple machine learning algorithms

Environmental Science and Pollution Research, Journal Year: 2022, Volume and Issue: 30(7), P. 18617 - 18630

Published: Oct. 10, 2022

Language: Английский

---

Physicochemical Parameters of Water and Its Implications on Avifauna and Habitat Quality

Sustainability, Journal Year: 2023, Volume and Issue: 15(12), P. 9494 - 9494

Published: June 13, 2023

Wetland ecosystems are essential for maintaining biological diversity and significant elements of the global landscape. However, biodiversity wetlands has been significantly reduced by more than 50% worldwide due to rapid expansion urban areas other human activities. The aforementioned factors have resulted in drastic antagonistic effects on species composition, particularly aquatic avifauna. decline wetland avifauna, which can be attributed changes water quality that impact habitats, is a major concern. In this study, we evaluated physicochemical parameters avifauna India’s first Conservation Reserve, Ramsar site an Important Bird Area. Water samples were collected monthly basis across nine different sites various parameters, such as temperature, electrical conductivity, pH, oxygen demand, dissolved oxygen, total solids salinity, analyzed pre-monsoon post-monsoon seasons, while point count surveys conducted assess richness density waterbirds. Our findings show positive correlation with temperature (r = 0.57), 0.56) 0.6) season negative −0.62) demand −0.69) season. We suggest synergistic effect may affect bird populations Asan Reserve. Poor was observed few sampling sites, negatively number waterbirds present. study emphasize importance conservation,

Language: Английский

---

Tracking changes in chlorophyll-a concentration and turbidity in Nansi Lake using Sentinel-2 imagery: A novel machine learning approach

Ecological Informatics, Journal Year: 2024, Volume and Issue: 81, P. 102597 - 102597

Published: April 9, 2024

This study represents the first application of Sentinel-2 remote sensing imagery and model fusion techniques to assess chlorophyll-a (Chla) concentration turbidity in Nansi Lake, Shandong Province, China, from 2016 2022. First, we innovatively employed stacking method fuse eight fundamentally different Machine Learning (ML) models, each utilising 20 17 feature bands, resulting development a robust algorithm for estimating Chla Lake. The results demonstrate that Stacking Model has achieved outstanding theoretical generalisation capability. Second, sensitivity extreme value data sample was quantified, found compared with gradient boosting (XGBoost), optimal performance improved by 12%, some extent, it solved problem high-value underestimation low-value overestimation. SHapley Additive exPlanations (SHAP) revealed features such as Three Bands, Enhanced Three, Rrs492/Rrs560, Rrs705/Rrs665 play crucial role concentration. For estimation, Normalized Difference Turbidity Index (NDTI), Rrs705+Rrs560, Rrs865-Rrs740 made significant contributions. Finally, utilised create spatiotemporal maps Lake We analysed causes water quality changes explored driving factors. Compared previous studies, this paper provides new idea monitoring lake parameters using high resolution image precision technology, these can provide reference similar area research decision-making support environment-related departments.

Language: Английский

---

Remote Data for Mapping and Monitoring Coastal Phenomena and Parameters: A Systematic Review

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(3), P. 446 - 446

Published: Jan. 23, 2024

Since 1971, remote sensing techniques have been used to map and monitor phenomena parameters of the coastal zone. However, updated reviews only considered one phenomenon, parameter, data source, platform, or geographic region. No review has offered an overview that can be accurately mapped monitored with data. This systematic was performed achieve this purpose. A total 15,141 papers published from January 2021 June 2023 were identified. The 1475 most cited screened, 502 eligible included. Web Science Scopus databases searched using all possible combinations between two groups keywords: geographical names in areas platforms. demonstrated that, date, many (103) (39) (e.g., coastline land use cover changes, climate change, urban sprawl). Moreover, authors validated 91% retrieved parameters, 39 1158 times (88% combined together other parameters), 75% over time, 69% several compared results each available products. They obtained 48% different methods, their 17% GIS model techniques. In conclusion, addressed requirements needed more effectively analyze employing integrated approaches: they data, merged

Language: Английский

---

Retrieval of Chlorophyll-a Concentrations Using Sentinel-2 MSI Imagery in Lake Chagan Based on Assessments with Machine Learning Models

Remote Sensing, Journal Year: 2022, Volume and Issue: 14(19), P. 4924 - 4924

Published: Oct. 1, 2022

Chlorophyll-a (Chl-a) is an important characterized parameter of lakes. Monitoring it accurately through remote sensing thus great significance for early warnings water eutrophication. Sentinel Multispectral Imager (MSI) images from May to September between 2020 and 2021 were used along with in-situ measurements estimate Chl-a in Lake Chagan, which located Jilin Province, Northeast China. In this study, the extreme gradient boosting (XGBoost) Random Forest (RF) models, had similar performances, generated by six single bands band combinations. The RF model was then selected based on assessments (R2 = 0.79, RMSE 2.51 μg L−1, MAPE 9.86%), since its learning input features conformed bio-optical properties Case 2 waters. study considered concentrations Chagan as a seasonal pattern according K-Nearest-Neighbors (KNN) classification. also showed relatively stable performance three seasons (spring, summer autumn) applied map whole lake. research presents more reliable machine (ML) higher precision than previous empirical shown effects linked biological mechanisms Chl-a. Its robustness revealed temporal spatial distributions concentrations, consistent map. This capable revealing current ecological situation can serve reference inland

Language: Английский

---

Machine learning-based water quality prediction using octennial in-situ Daphnia magna biological early warning system data

Journal of Hazardous Materials, Journal Year: 2023, Volume and Issue: 465, P. 133196 - 133196

Published: Dec. 8, 2023

Language: Английский

---

Water Quality Prediction of Small-Micro Water Body Based on the Intelligent-Algorithm-Optimized Support Vector Machine Regression Method and Unmanned Aerial Vehicles Multispectral Data

Sustainability, Journal Year: 2024, Volume and Issue: 16(2), P. 559 - 559

Published: Jan. 9, 2024

Accurate prediction of spatial variation in water quality small microwaters remains a challenging task due to the complexity and inherent limitations optical properties microwaters. In this paper, based on unmanned aerial vehicles (UAV) multispectral images amount measured data, performance seven intelligent algorithm-optimized SVR models predicting concentration chlorophyll (Chla), total phosphorus (TP), ammonia nitrogen (NH3-N), turbidity (TUB) micro bodies were compared analyzed. The results show that Gray Wolf optimized model (GWO-SVR) has highest comprehensive performance, with R2 0.915, 0.827, 0.838, 0.800, respectively. addition, even when dealing limited training samples different data periods, GWO-SVR also shows remarkable stability portability. Finally, according forecast results, influencing factors pollution discussed. This method practical significance improving intelligence level body monitoring.

Language: Английский

---

Long-term monitoring chlorophyll-a concentration using HJ-1 A/B imagery and machine learning algorithms in typical lakes, a cold semi-arid region

Optics Express, Journal Year: 2024, Volume and Issue: 32(9), P. 16371 - 16371

Published: April 9, 2024

Chlorophyll a (Chl-a) in lakes serves as an effective marker for assessing algal biomass and the nutritional level of lakes, its observation is feasible through remote sensing methods. HJ-1 (Huanjing-1) satellite, deployed 2008, incorporates CCD capable 30 m resolution has revisit interval 2 days, rendering it superb choice or supplemental sensor monitoring trophic state lakes. For long-term regional-scale mapping, both imagery evaluation machine learning algorithms are essential. The several typical algorithms, i.e., Support Vector Regression (SVR), Gradient Boosting Decision Trees (GBDT), XGBoost (XGB), Random Forest (RF), K-Nearest Neighbor (KNN), Kernel Ridge (KRR), Multi-Layer Perception Network (MLP), were developed using our in-situ measured Chl-a. A cross-validation grid to identify most hyperparameter combinations each algorithm was used, well selected optimal superparameter combinations. In Chl-a mapping three R2 GBDT, XGB, RF, KRR all reached 0.90, while XGB also exhibited stable performance with smallest error (RMSE = 3.11 μg/L). Adjustments made align spatial-temporal patterns past data, utilizing HJ1-A/B images algorithm, which demonstrates stability. Our results highlight considerable effectiveness utility A/B cold arid region, providing application cases contribute ongoing efforts monitor water qualities.

Language: Английский

---

Using Ensemble Learning for Remote Sensing Inversion of Water Quality Parameters in Poyang Lake

Sustainability, Journal Year: 2024, Volume and Issue: 16(8), P. 3355 - 3355

Published: April 17, 2024

Inland bodies of water, such as lakes, play a crucial role in sustaining life and supporting ecosystems. However, with the rapid development socio-economics, water resources are facing serious pollution problems, eutrophication degradation wetlands. Therefore, monitoring, management, protection inland particularly important. In past research, empirical models machine learning have been widely used for quality assessment lakes. Due to complexity optical properties lake bodies, performance these is often limited. To overcome limitations models, this study uses situ data from 2017 2018 multispectral (MS) remote sensing Sentinel-2 construct experimental samples Poyang Lake. Based on samples, we constructed spatio-temporal ensemble model (STE) evaluate four common parameters: chlorophyll-a (Chl-a), total phosphorus (TP), nitrogen (TN), chemical oxygen demand (COD). The adopts an strategy, improving model’s by merging multiple advanced algorithms. We introduced several indices related parameters auxiliary variables, NDCI Enhanced Three, band variables predictive thereby greatly enhancing potential model.The results show that inversion accuracy high (R2 0.94, 0.88, 0.92, 0.93; RMSE 1.15, 0.01, 0.02, 0.02; MAE 0.81, 0.09, 0.10), indicating STE has good evaluation accuracy. Meanwhile, reveal distribution Chl-a, TP, TN, COD 2018, analyzed their seasonal spatial variation rules. not only provide effective practical method monitoring managing but also security socio-economic ecological environmental safety.

Language: Английский

---