A stacking ANN ensemble model of ML models for stream water quality prediction of Godavari River Basin, India

Ecological Informatics, Journal Year: 2024, Volume and Issue: 80, P. 102500 - 102500

Published: Jan. 28, 2024

The importance of water quality models has increased as their inputs are critical to the development risk assessment framework for environmental management and monitoring rivers. However, with advent a plethora recent advances in ML algorithms better predictions possible. This study proposes causal effect model by considering climatological such temperature precipitation along geospatial information related agricultural land use factor (ALUF), forest (FLUF), grassland usage (GLUF), shrub (SLUF), urban (ULUF). All these factors included input data, whereas four Stream Water Quality parameters (SWQPs) Electrical Conductivity (EC), Biochemical Oxygen Demand (BOD), Nitrate, Dissolved (DO) from 2019 2021 taken outputs predict Godavari River Basin quality. In preliminary investigation, out SWQPs, nitrate's coefficient variation (CV) is high, revealing close association climate practices across sampling stations. authors' earlier study, using single-layer Feed-Forward Neural Network (FFNN) showed improved performance predicting cause linked metrics. To achieve prediction, stacked ANN meta-model nine conventional machine learning (ML) models, including Extreme Gradient Boosting (XGB), Extra Trees (ET), Bagging (BG), Random Forest (RF), AdaBoost or Adaptive (ADB), Decision Tree (DT), Highest (HGB), Light Method (LGBM), (GB), were compared this study. According study's findings, outperformed stand-alone FFNN same dataset superior predictive capabilities terms accuracy forecasting variable interest. For instance, during testing, determination (R2) (BOD) 0.72 0.87. Furthermore, Artificial (ANN) meta that was reinforced (ET) base performed than individual (from R2 = 0.87 0.91 BOD testing). By new framework, effort hyperparameter tuning can be minimized.

Language: Английский

---

Revolutionizing the Future of Hydrological Science: Impact of Machine Learning and Deep Learning amidst Emerging Explainable AI and Transfer Learning

Applied Computing and Geosciences, Journal Year: 2024, Volume and Issue: 24, P. 100206 - 100206

Published: Nov. 9, 2024

Language: Английский

---

Food Security Based Marine Life Ecosystem for Polar Region Conditioning: Remote Sensing Analysis with Machine Learning Model

Remote Sensing in Earth Systems Sciences, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 11, 2024

Language: Английский

---

Climate change effects on animal presence in the Massaciuccoli Lake basin

Ecological Informatics, Journal Year: 2024, Volume and Issue: 81, P. 102644 - 102644

Published: May 16, 2024

Big-data mining approaches based on Artificial Intelligence models can help forecast biodiversity changes before they happen. These predict macroscopic species distribution patterns and trends that inform preventive measures to avoid the loss of ecosystem functions services. They can, therefore, study mitigate climate change implications conservation in fragile ecosystems. Wetlands are particularly ecosystems where poses severe risks has dramatically reduced their size over past century, with profound consequences Through big-data approaches, we future wetland context change. This paper proposes such predictive analysis for a specific wetland: The Massaciuccoli Lake basin Tuscany, Italy. is critical tourist attraction due its rich biodiversity, making it an area interest citizens, tourists, scientists. However, region's suitability native non-native at risk land-use Using machine-learning models, potential effects animal spatial under different greenhouse gas emission scenarios. results suggest habitat generally improved from 1950 today, presumably owing targeted strategies adopted area, but will severely reduce bird by 2050 while favouring several insect species' proliferation other change, even medium-emission scenario. lead significant basin's biodiversity. Our methodology adaptable basins, being fully open data models. spatially explicit modelling used this research provides valuable information policymakers planners, complementing traditional trend analyses.

Language: Английский

---

Estimation of phytoplankton community composition from satellite data using a fuzzy and probabilistic combination model in mountainous reservoirs: A case of Huating Lake in spring and summer

Ecological Informatics, Journal Year: 2025, Volume and Issue: unknown, P. 103153 - 103153

Published: April 1, 2025

Language: Английский

---

Contributions of source populations, habitat suitability and trait overlap to benthic invertebrate community assembly in restored urban streams

Ecological Processes, Journal Year: 2025, Volume and Issue: 14(1)

Published: April 25, 2025

Abstract Background Understanding the temporal development of community assembly processes is essential for assessing recovery degraded ecosystems after restoration. Community in restored streams often slow or absent, due to inadequate restoration, catchment-scale pressures, and/or colonisation barriers. Recovery involve three key filters: dispersal, environmental conditions and biotic interactions. Dispersal critical initial colonisation, while influence successful population establishment. Lastly, as available niches fill, interactions, such competition, gain importance. Despite presence many theories on how these filters interact during assembly, they have rarely been investigated simultaneously. Our detailed species- site-specific approach allowed us analyse a hierarchical analysis. We assessed effect filters, by examining benthic invertebrate communities at 20 sites Boye catchment (Western Germany). The most its tributaries were used open sewers century, i.e. concrete channels transporting untreated sewage before gradual restoration was started 1990s. bank reinforcements beds removed, riparian vegetation left natural succession. Accordingly, grouped 'unimpacted', 'recently restored' (< 4 years), 'mature (> 10 years). An additional 28 provided information distances source populations, species’ habitat suitability filtering. Biotic (interaction) filtering evaluated through trait overlap Results Communities recently differed from mature unimpacted sites, resembled ones. Taxa had nearer those better matched present habitats. Trait did not differ between absent taxa. Conclusions results indicate that dispersal early stages, with mass effects upstream sources supporting taxa found despite low suitability. Over time, became more influential, shaping communities. Competition appeared relatively unimportant, yet competitive exclusion may explain small proportions sites. Hence, effectively support stream recovery, it consider different operate various stages process. For example, could further develop if availability increases, connectivity populations would only play minor role.

Language: Английский

---

A data-driven approach for the assessment of the thermal stratification of reservoirs based on readily available data

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102672 - 102672

Published: June 10, 2024

A data-driven approach to assess the occurrence of thermal stratification and depth thermocline in water masses has been developed tested Spanish reservoir El Val. The novelty this is that it relies only on readily available data can be collected for almost any reservoir, providing managers with a transferable tool easily adapted other reservoirs or lakes. input variables were meteorological data, level output flow. non-supervised clustering technique, k-means, was used identify period unlabelled say inferring patterns when from target variable not available. As supervised method, Artificial Neural Networks classify given day as having and, positive case, infer thermocline. classification showed very high accuracy (96%) estimation mean absolute error (MAE) 1.94 m 1.99 training test fractions, respectively. Shapley Additive Explanations (SHAP) values improve explainability they revealed most important features level, daily average solar irradiance air temperature.

Language: Английский

---

Simulation and control of the cyanobacterial bloom biomass in a typical plateau lake based on the logistic growth model: A case study of Xingyun Lake

Ecological Informatics, Journal Year: 2024, Volume and Issue: 82, P. 102779 - 102779

Published: Aug. 23, 2024

The simulation and early warning of cyanobacterial blooms in lakes are great significance. Controlling the growth cyanobacteria plateau is challenging due to unique geographical environment, climatic conditions, impact anthropogenic activities. Therefore, conducting simulations crucial effectively control lakes. This study aimed investigate Xingyun Lake, a representative lake China, using logistic model analyze patterns assess effects projects, along with influence meteorological environmental factors. Moreover, proposed method for establishing curves ranges managing blooms. results demonstrated that chlorophyll-a concentration effluent decreased by an average 97.74% compared influent after implementing integrated "deep-well pressure algal control" "ecological purification algae-water separation" processes Lake. total annual decrease was approximately 3.40 times lake's content. Lake followed pattern during blooming period, before projects (from 2018 2022), overall trend from 2010 2022 aligning model. identified lower temperatures precipitation, reduced nitrogen phosphorus loads, higher nitrogen-to‑phosphorus ratio as main factors inhibiting growth. Establishing sustaining project transition point maximum attenuated rate throughout year. offered novel perspectives preventing controlling blooms, offering practical guidance management, especially regions. • Case management performed. effectiveness evaluated. bloom period. Temperature, influenced were established.

Language: Английский

---

Process-based forecasts of lake water temperature and dissolved oxygen outperform null models, with variability over time and depth

Ecological Informatics, Journal Year: 2024, Volume and Issue: 83, P. 102825 - 102825

Published: Sept. 11, 2024

Language: Английский

---

Marine Life Ecosystem Analysis Based on Climate Change Detection Using Deep Learning Algorithms

Remote Sensing in Earth Systems Sciences, Journal Year: 2025, Volume and Issue: unknown

Published: March 19, 2025

Language: Английский

---