A comprehensive water quality assessment for a typical river–lake watershed in Northeast China: implications for the water management of boundary lake
Notice bibliographique
Résumé
• An improved water quality index (WQI) model was established based on machine learning algorithm. • The WQI condition of 60%−70% monitoring stations in the Muling-Xingkai watershed was good. • River water quality was worse than that of reservoirs and lakes, especially in summer-autumn. • Main driving factors for water quality deterioration differ in summer-autumn and winter-spring. • Nitrogen input and endogenous phosphorus release should be curbed to protect Xingkai Lake. Seasonal freezing and a mismatch between river and lake water quality targets have limited the accurate evaluation of water quality in the northern river–lake system. The water quality of the boundary lake poses a threat to aquatic ecological security and may also affect regional geopolitical stability. Therefore, there is an urgent need for a comprehensive water quality evaluation system to effectively manage the water health of boundary lakes. In this study, we aimed to develop a new comprehensive water quality index model to analyze the water quality status and identify the underlying driving mechanisms within the Muling-Xingkai watershed, thereby proposing effective water management strategies. The XGBoost model and the aggregation function of eight sub-indicators were employed to identify the primary control indicators across various seasons. These methods reduced data redundancy and enhanced the sensitivity of the comprehensive water quality index (WQI) model. The weighted harmonic mean model ( R 2 = 0.95, RMSE = 7.1 for summer-autumn; R 2 = 0.96, RMSE = 10.2 for winter-spring) and unweighted Canadian Council of Ministers of the Environment model ( R 2 = 0.94, RMSE = 4.2 for summer-autumn; R 2 = 0.90, RMSE = 4.8 for winter-spring) were identified as the optimal functions for water quality assessment. Based on the WQI assessment of 480 water samples collected during 2022–2023, 60 % to 70 % of the monitoring stations achieved a good water quality status (WQI score > 80) in the Muling-Xingkai watershed. The water quality status within the watershed, as assessed by the WQI model, followed the order: river < reservoir < Xingkai Lake < Xiaoxingkai Lake. In addition, our systematic approach efficiently identified key water quality indicators from 11 types of indicators, including total nitrogen (TN), total phosphorus (TP), and water temperature (Tw) during the summer-autumn period, and TN and dissolved oxygen (DO) in the winter-spring period. Based on structural equation modeling (SEM), human activities (irrigated area, fertilizer application rate) and natural factors (air temperature, precipitation, and flow) were identified as the primary driving forces behind water quality deterioration in the Muling-Xingkai watershed during the summer-autumn and winter-spring seasons, respectively. To safeguard the ecological health of Xingkai Lake, it is imperative to reduce nitrogen inputs from the Muling River and mitigate phosphorus release from lake sediments in response to climate warming and the expansion of irrigation districts.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,001 | 0,001 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,000 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,001 | 0,001 |
| Études des sciences et des technologies | 0,001 | 0,000 |
| Communication savante | 0,001 | 0,001 |
| Science ouverte | 0,001 | 0,001 |
| Intégrité de la recherche | 0,001 | 0,000 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,001 | 0,000 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule source (Gemma direct ou Codex distillé), pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».