Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake Bay
Total suspended solids (TSS) is an important environmental parameter to monitor in the Chesapeake Bay due to its effects on submerged aquatic vegetation, pathogen abundance, and habitat damage for other aquatic life. Chesapeake Bay is home to an extensive and continuous network of in situ water qual...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2018-09-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | http://www.mdpi.com/2072-4292/10/9/1393 |
_version_ | 1819289061614944256 |
---|---|
author | Nicole M. DeLuca Benjamin F. Zaitchik Frank C. Curriero |
author_facet | Nicole M. DeLuca Benjamin F. Zaitchik Frank C. Curriero |
author_sort | Nicole M. DeLuca |
collection | DOAJ |
description | Total suspended solids (TSS) is an important environmental parameter to monitor in the Chesapeake Bay due to its effects on submerged aquatic vegetation, pathogen abundance, and habitat damage for other aquatic life. Chesapeake Bay is home to an extensive and continuous network of in situ water quality monitoring stations that include TSS measurements. Satellite remote sensing can address the limited spatial and temporal extent of in situ sampling and has proven to be a valuable tool for monitoring water quality in estuarine systems. Most algorithms that derive TSS concentration in estuarine environments from satellite ocean color sensors utilize only the red and near-infrared bands due to the observed correlation with TSS concentration. In this study, we investigate whether utilizing additional wavelengths from the Moderate Resolution Imaging Spectroradiometer (MODIS) as inputs to various statistical and machine learning models can improve satellite-derived TSS estimates in the Chesapeake Bay. After optimizing the best performing multispectral model, a Random Forest regression, we compare its results to those from a widely used single-band algorithm for the Chesapeake Bay. We find that the Random Forest model modestly outperforms the single-band algorithm on a holdout cross-validation dataset and offers particular advantages under high TSS conditions. We also find that both methods are similarly generalizable throughout various partitions of space and time. The multispectral Random Forest model is, however, more data intensive than the single band algorithm, so the objectives of the application will ultimately determine which method is more appropriate. |
first_indexed | 2024-12-24T03:00:52Z |
format | Article |
id | doaj.art-57c127a29df94ec187cf05f47ae49f51 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-12-24T03:00:52Z |
publishDate | 2018-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-57c127a29df94ec187cf05f47ae49f512022-12-21T17:18:12ZengMDPI AGRemote Sensing2072-42922018-09-01109139310.3390/rs10091393rs10091393Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake BayNicole M. DeLuca0Benjamin F. Zaitchik1Frank C. Curriero2Department of Earth and Planetary Sciences, Johns Hopkins University, 3400 N. Charles Street, Olin Hall, Baltimore, MD 21218, USADepartment of Earth and Planetary Sciences, Johns Hopkins University, 3400 N. Charles Street, Olin Hall, Baltimore, MD 21218, USADepartment of Epidemiology, Johns Hopkins Bloomberg School of Public Health, Johns Hopkins University, 615 N. Wolf Street, Baltimore, MD 21205, USATotal suspended solids (TSS) is an important environmental parameter to monitor in the Chesapeake Bay due to its effects on submerged aquatic vegetation, pathogen abundance, and habitat damage for other aquatic life. Chesapeake Bay is home to an extensive and continuous network of in situ water quality monitoring stations that include TSS measurements. Satellite remote sensing can address the limited spatial and temporal extent of in situ sampling and has proven to be a valuable tool for monitoring water quality in estuarine systems. Most algorithms that derive TSS concentration in estuarine environments from satellite ocean color sensors utilize only the red and near-infrared bands due to the observed correlation with TSS concentration. In this study, we investigate whether utilizing additional wavelengths from the Moderate Resolution Imaging Spectroradiometer (MODIS) as inputs to various statistical and machine learning models can improve satellite-derived TSS estimates in the Chesapeake Bay. After optimizing the best performing multispectral model, a Random Forest regression, we compare its results to those from a widely used single-band algorithm for the Chesapeake Bay. We find that the Random Forest model modestly outperforms the single-band algorithm on a holdout cross-validation dataset and offers particular advantages under high TSS conditions. We also find that both methods are similarly generalizable throughout various partitions of space and time. The multispectral Random Forest model is, however, more data intensive than the single band algorithm, so the objectives of the application will ultimately determine which method is more appropriate.http://www.mdpi.com/2072-4292/10/9/1393Chesapeake Baywater qualitymultispectralocean colortotal suspended solidssatellite remote sensingstatistical analysismachine learningRandom Forest |
spellingShingle | Nicole M. DeLuca Benjamin F. Zaitchik Frank C. Curriero Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake Bay Remote Sensing Chesapeake Bay water quality multispectral ocean color total suspended solids satellite remote sensing statistical analysis machine learning Random Forest |
title | Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake Bay |
title_full | Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake Bay |
title_fullStr | Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake Bay |
title_full_unstemmed | Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake Bay |
title_short | Can Multispectral Information Improve Remotely Sensed Estimates of Total Suspended Solids? A Statistical Study in Chesapeake Bay |
title_sort | can multispectral information improve remotely sensed estimates of total suspended solids a statistical study in chesapeake bay |
topic | Chesapeake Bay water quality multispectral ocean color total suspended solids satellite remote sensing statistical analysis machine learning Random Forest |
url | http://www.mdpi.com/2072-4292/10/9/1393 |
work_keys_str_mv | AT nicolemdeluca canmultispectralinformationimproveremotelysensedestimatesoftotalsuspendedsolidsastatisticalstudyinchesapeakebay AT benjaminfzaitchik canmultispectralinformationimproveremotelysensedestimatesoftotalsuspendedsolidsastatisticalstudyinchesapeakebay AT frankccurriero canmultispectralinformationimproveremotelysensedestimatesoftotalsuspendedsolidsastatisticalstudyinchesapeakebay |