Effects of satellite temporal resolutions on the remote derivation of trends in phytoplankton blooms in inland waters

Zhang, Yuchao; Shi, Kun; Cao, Zhen; Lai, Lai; Geng, Jiawei; Yu, Kuiting; Zhan, Peng; Liu, Zhaomin

doi:10.1016/j.isprsjprs.2022.07.017

Cited by 21 publications

(6 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach ensures a maximum level of correction accuracy, even in the presence of unavoidable errors. Furthermore, the alignment of time windows [56] and pixel window [57] sizes for onsite estimations and satellite data introduces error sources within the retrieval model. While Sentinel-2 MSI imagery follows a five-day orbital cycle, practical limitations arising from adverse weather conditions considerably restrict the number of images that effectively align with measured data.…”

Section: Analysis Of Error Sources Affecting Model Performancementioning

confidence: 99%

Retrieval of Water Quality Parameters in Dianshan Lake Based on Sentinel-2 MSI Imagery and Machine Learning: Algorithm Evaluation and Spatiotemporal Change Research

Dong,

Gong,

Huai

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

According to current research, machine learning algorithms have been proven to be effective in detecting both optical and non-optical parameters of water quality. The use of satellite remote sensing is a valuable method for monitoring long-term changes in the quality of lake water. In this study, Sentinel-2 MSI images and in situ data from the Dianshan Lake area from 2017 to 2023 were used. Four machine learning methods were tested, and optimal detection models were determined for each water quality parameter. It was ultimately determined that these models could be applied to long-term images to analyze the spatiotemporal variations and distribution patterns of water quality in Dianshan Lake. Based on the research findings, integrated learning algorithms, especially CatBoost, have achieved good results in the retrieval of all water quality parameters. Spatiotemporal analysis reveals that the overall distribution of water quality parameters is uneven, with significant spatial variations. Permanganate index (CODMn), Total Nitrogen (TN), and Total Phosphorus (TP) show relatively small interannual differences, generally exhibiting a decreasing trend in concentrations. In contrast, chlorophyll-a (Chl-a), dissolved oxygen (DO), and Secchi Disk Depth (SDD) exhibit significant interannual and inter-year differences. Chl-a reached its peak in 2020, followed by a decrease, while DO and SDD showed the opposite trend. Further analysis indicated that the distribution of water quality parameters is significantly influenced by climatic factors and human activities such as agricultural expansion. Overall, there has been an improvement in the water quality of Dianshan Lake. The study demonstrates the feasibility of accurately monitoring water quality even without measured spectral data, using machine learning methods and satellite reflectance data. The research results presented in this paper can provide new insights into water quality monitoring and water resource management in Dianshan Lake.

show abstract

Section: Analysis Of Error Sources Affecting Model Performancementioning

confidence: 99%

Retrieval of Water Quality Parameters in Dianshan Lake Based on Sentinel-2 MSI Imagery and Machine Learning: Algorithm Evaluation and Spatiotemporal Change Research

Dong,

Gong,

Huai

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Environmental data such as climate and remote sensing data sets are essential for understanding the dynamics of the Earth's climate system and predicting future changes in the environment [1][2][3]. However, many climate and remote sensing datasets have a low temporal resolution, typically recorded at daily or monthly intervals [4,5]. The limited temporal resolution of these data sets presents significant challenges in extracting detailed insights and limits their utility for analyzing rapid, transient events [6,7].…”

Section: Introductionmentioning

confidence: 99%

Interpolation of environmental data using deep learning and model inference

Ibebuchi,

Abu

2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

The temporal resolution of environmental data sets plays a major role in the granularity of the information that can be derived from the data. In most cases, it is required that different data sets have a common temporal resolution to enable their consistent evaluations and applications in making informed decisions. This study leverages deep learning with long short-term memory (LSTM) neural networks and model inference to enhance the temporal resolution of climate datasets, specifically temperature, and precipitation, from daily to sub-daily scales. We trained our model to learn the relationship between daily and sub-daily data, subsequently applying this knowledge to increase the resolution of a separate dataset with a coarser (daily) temporal resolution. Our findings reveal a high degree of accuracy for temperature predictions, evidenced by a correlation of 0.99 and a mean absolute error of 0.21 °C, between the actual and predicted sub-daily values. In contrast, the approach was less effective for precipitation, achieving an explained variance of only 37%, compared to 98% for temperature. Further, besides the sub-daily interpolation of the climate data sets, we adapted our approach to increase the resolution of the Normalized difference vegetation index of Landsat (from 16-day to 5-day interval) using the LSTM model pre-trained from the Sentinel 2 Normalized difference vegetation index - that exists at a relatively higher temporal resolution. The explained variance between the predicted Landsat and Sentinel 1 data is 70% with a mean absolute error of 0.03. These results suggest that our method is particularly suitable for environmental datasets with less pronounced short-term variability, offering a promising tool for improving the resolution and utility of the data.

show abstract

“…Therefore, more high-frequency observations are needed to improve the acquisition of information on highly dynamic aquatic environments under varying weather conditions, which could play a key role in developing early warning, early prevention, and early disposal strategies to control cyanobacterial blooms and ensure the safety of urban drinking water. Cyanobacteria dynamics represent an important scientific topic, and previous related studies have confirmed that it is difficult to objectively reveal long-term cyanobacteria dynamics using only satellite data with low temporal resolution [18]. High-frequency satellite observations would minimize the amount of missing information due to cloud cover, which could ensure a more accurate evaluation of cyanobacterial bloom events, help improve understanding of cyanobacteria dynamics, and reduce the uncertainty of estimations of carbon fixation associated with cyanobacterial blooms [19].…”

Section: Introductionmentioning

confidence: 99%

High-Frequency Observations of Cyanobacterial Blooms in Lake Taihu (China) from FY-4B/AGRI

Xin

Zhu

et al. 2023

Water

View full text Add to dashboard Cite

China’s FY-4B satellite, launched on 3 June 2021, is a new-generation geostationary meteorological satellite. The Advanced Geosynchronous Radiation Imager (AGRI) onboard FY-4B has 15 spectral channels, including 2 visible (470 and 650 nm), 1 near infrared (825 nm), and 3 shortwave infrared (1379, 1610, and 2225 nm) bands, which can be used to observe the Earth system with the highest spatial resolution of 500 m and 15 min temporal resolution. In this study, FY-4B/AGRI observations were applied for the first time to monitor cyanobacterial blooms in Lake Taihu, China. The AGRI reflectance at visible and near-infrared bands was first corrected to surface reflectance using the 6S radiative transfer model. Due to the similar spectral reflectance characteristics to those of land-based vegetation, the normalized difference vegetation index (NDVI) and some other remote sensing vegetation indices are usually used for the retrieval of cyanobacterial blooms. The fractional vegetation cover (FVC) of algae, defined as the fraction of green vegetation in the nadir view, was adopted to depict the status and trend of cyanobacterial blooms. NDVI and FVC, the two remote sensing indices developed for the retrieval of land vegetation, were used for the detection of cyanobacteria blooms in Lake Taihu. Finally, the FVC derived from AGRI measurements was compared with that obtained from the Advanced Himawari Imager (AHI) onboard the Himawari-8 satellite to validate the effectiveness of our method. It was found that atmospheric correction can substantially improve the determination of the normalized difference vegetation index (NDVI) values of cyanobacterial blooms in the lake. As a proof of the robustness of the algorithm, the NDVIs are both derived from both AGRI and AHI and their magnitudes are similar. In addition, the distribution of cyanobacterial blooms derived from AGRI FVC is highly consistent with that derived from FY-3D/MERSI and EOS/MODIS. While a lower spatial resolution of FY-4B/AGRI might restrict its capability in capturing some spatial details of cyanobacterial blooms, the high-frequency measurements can provide information for the timely and effective management of aquatic ecosystems and help researchers better quantify and understand the dynamics of cyanobacterial blooms. In particular, AGRI can provide greater details on the diurnal variation in the distribution of cyanobacterial blooms owing to the high temporal resolution.

show abstract

Effects of satellite temporal resolutions on the remote derivation of trends in phytoplankton blooms in inland waters

Cited by 21 publications

References 62 publications

Retrieval of Water Quality Parameters in Dianshan Lake Based on Sentinel-2 MSI Imagery and Machine Learning: Algorithm Evaluation and Spatiotemporal Change Research

Retrieval of Water Quality Parameters in Dianshan Lake Based on Sentinel-2 MSI Imagery and Machine Learning: Algorithm Evaluation and Spatiotemporal Change Research

Interpolation of environmental data using deep learning and model inference

High-Frequency Observations of Cyanobacterial Blooms in Lake Taihu (China) from FY-4B/AGRI

Contact Info

Product

Resources

About