Skip to content
DraconiticResearch
Search Sources API
186,123 studies31 sourcesUpdated 13 min ago
PreprintCC BY-NC 4.0EarthArXiv

A comprehensive evaluation of inland water quality monitoring using the long-term Landsat archive and mixture density networks

  • Lorena Pinheiro Silva
  • Xiaoxu Guo
  • Rebecca Lee North
  • Greg Silsbe
Open at sourcePDFDOICite

Abstract

Nutrient enrichment of inland and coastal waters is visible from space. In these regions, chlorophyll a (chl-a), total suspended solids (TSS), and Secchi depth (ZSD) constitute the most commonly targeted water quality parameters. A growing number of studies have shown that, despite not being strictly optically active, total nitrogen (TN) and total phosphorus (TP) can nonetheless be estimated from remotely sensed data with varying accuracy, underscoring that in some environments water color is a robust indicator of trophic state. This study provides a comprehensive analysis of Mixture Density Networks (MDN) model performance across a suite of water quality parameters (TN, TP, chl-a, ZSD, and TSS) using Landsat 7–9 co-located with nearly 100 sampled reservoirs in Missouri, USA. MDN models were deployed across several pipelines that represent different combinations of atmospheric correction processors (LEDAPS/LaSRC, ACOLITE, and RAdCor), matchup windows (within 1 and 3 -day), feature engineering strategies (single versus multi-feature input), and model output configurations (single versus multiple-output). The median symmetric accuracy (MdSA) of model predictions was variable across parameters and pipelines. TN had the best-performing pipeline (MdSA=16.1%) and pipeline ensemble (MdSA=25.9%) followed by ZSD, TSS, and TP. Chl-a had worst ensemble accuracy (MdSA=71.1%) and was consistently the least accurate water quality metric across pipelines. That in this dataset definitive metrics of eutrophication that include non-optically active constituents (TN and TP) can be more accurately estimated than the most widely targeted water quality parameter (chl-a) is discussed from theoretical and applied perspectives.

Related

  1. Annual canopy height mapping in Italy from Landsat and multi-source LiDAR for disturbance and recovery monitoring
    Yang Su, Nikola Besic, Saverio Francini +14
    Ecological InformaticsPeer-reviewedCC BY 4.0Full textGeneral biologyEnvironmental science & pollutionHAL
  2. Decadal dynamics of surface water extent and quality in Fujian Province, China: An integrated optical-SAR remote sensing analysis using Landsat and Sentinel-1 time series (2015–2024)
    Muhammad Irfan Ahamad, Yuping Su, Zabih Ullah +3
    Ecological IndicatorsPeer-reviewedCC BYFull textEnvironmental science & pollutionDOAJ
  3. How much does the graph help? An information-parity evaluation of graph neural networks for urban air-quality estimation
    Valentino Petrić, Dejan Strbad, Nikolina Račić +6
    ChemRxivPreprintCC BYFull textEnvironmental science & pollutionChemRxiv
  4. CAT-GAN-UKF: uncertainty-aware spatiotemporal reconstruction for resilient urban air-quality monitoring under partial observability
    Lior Tobaly, Zeev Zalevsky, Eyal Yaniv
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEnvironmental science & pollutionCrossref
  5. Screening for Chemical Compliance in Water Quality Monitoring with In Vitro Bioassays
    Tessa E. Pronk, Miina Yanagihara, Corine J. Houtman +2
    Environmental science & technology lettersPeer-reviewedCC BYFull textEnvironmental science & pollutionEurope PMC

Cite

BibTeXRIS
BibTeX
@misc{silva2026comprehensive,
  title = {{A comprehensive evaluation of inland water quality monitoring using the long-term Landsat archive and mixture density networks}},
  author = {Lorena Pinheiro Silva and Xiaoxu Guo and Rebecca Lee North and Greg Silsbe},
  howpublished = {EarthArXiv},
  year = {2026},
  month = sep,
  doi = {10.31223/x58z29},
  url = {https://eartharxiv.org/repository/view/14734/},
  note = {CC BY-NC 4.0},
}
RIS
TY  - UNPB
TI  - A comprehensive evaluation of inland water quality monitoring using the long-term Landsat archive and mixture density networks
AU  - Lorena Pinheiro Silva
AU  - Xiaoxu Guo
AU  - Rebecca Lee North
AU  - Greg Silsbe
PY  - 2026
DA  - 2026/09/01
PB  - EarthArXiv
DO  - 10.31223/x58z29
UR  - https://eartharxiv.org/repository/view/14734/
AB  - Nutrient enrichment of inland and coastal waters is visible from space. In these regions, chlorophyll a (chl-a), total suspended solids (TSS), and Secchi depth (ZSD) constitute the most commonly targeted water quality parameters. A growing number of studies have shown that, despite not being strictly optically active, total nitrogen (TN) and total phosphorus (TP) can nonetheless be estimated from remotely sensed data with varying accuracy, underscoring that in some environments water color is a robust indicator of trophic state. This study provides a comprehensive analysis of Mixture Density Networks (MDN) model performance across a suite of water quality parameters (TN, TP, chl-a, ZSD, and TSS) using Landsat 7–9 co-located with nearly 100 sampled reservoirs in Missouri, USA. MDN models were deployed across several pipelines that represent different combinations of atmospheric correction processors (LEDAPS/LaSRC, ACOLITE, and RAdCor), matchup windows (within 1 and 3 -day), feature engineering strategies (single versus multi-feature input), and model output configurations (single versus multiple-output). The median symmetric accuracy (MdSA) of model predictions was variable across parameters and pipelines. TN had the best-performing pipeline (MdSA=16.1%) and pipeline ensemble (MdSA=25.9%) followed by ZSD, TSS, and TP. Chl-a had worst ensemble accuracy (MdSA=71.1%) and was consistently the least accurate water quality metric across pipelines. That in this dataset definitive metrics of eutrophication that include non-optically active constituents (TN and TP) can be more accurately estimated than the most widely targeted water quality parameter (chl-a) is discussed from theoretical and applied perspectives.
ER  -