scholarly journals Monitoring the effect of upwelling on the chlorophyll a distribution in the Gulf of Finland (Baltic Sea) using remote sensing and in situ data**The study was supported by the Estonian Science Foundation (grants No. 7467, No. 6752, No. 7633, No. 7581 & No. 8968). The remote sensing data were provided by ESA via Cat-1 project No. 6855.

Oceanologia ◽  
2012 ◽  
Vol 54 (3) ◽  
pp. 395-419 ◽  
Author(s):  
Rivo Uiboupin ◽  
Jaan Laanemets ◽  
Liis Sipelgas ◽  
Laura Raag ◽  
Inga Lips ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Baltic Sea ◽  
Chlorophyll A ◽  
Remote Sensing Data ◽  
Gulf Of Finland ◽  
Sensing Data ◽  
In Situ Data ◽  
The Gulf Of Finland ◽  
Chlorophyll A Distribution

scholarly journals Trophic status assessment of small turbid lakes comparing remote sensing and in situ data: case study at lower Danube floodplain

2020 ◽  
Vol 32 ◽  
pp. 53-63
Author(s):  
Stefan Kazakov ◽  
Valko Biserkov ◽  
Luchezar Pehlivanov ◽  
Stoyan Nedkov
Keyword(s):  
Remote Sensing ◽  
Chlorophyll A ◽  
Satellite Data ◽  
Suspended Matter ◽  
Trophic Status ◽  
Remote Sensing Data ◽  
Water Quality Monitoring ◽  
Floodplain Lakes ◽  
In Situ Data

The aim of the study was to compare in situ and remote sensing data, in order to assess the applicability of satellite images in water quality monitoring of floodplain lakes. Two indicators of trophic status were compared: chlorophyll a and total suspended matter. Two lakes on Lower Danube floodplain were selected: Srebarna and Malak Preslavets. Data were obtained in July and August 2018. Sentinel 2 MSI L1c images were analyzed in SeNtinel Application Platform (SNAP), (v. 6.0). According to in situ data, Srebarna Lake indicated status of eutrophication, while Malak Preslavets experienced hypertrophic conditions. Satellite data indicated eutrophic conditions for both lakes. Comparing the results from in situ and satellite data, chlorophyll a showed higher correlation (r = 0.66) and comparable results. On the other hand, significantly overestimation of suspended matter according to satellite data were found, as well weaker correlation (r = 0.57) between both methods. Remote sensing i.e. Sentinel products are emerging as a powerful tool in environmental observation. Although weather conditions could have significant impact on environmental dynamic especially in floodplain lakes, combining and comparing of different methods could improve the preciseness of the methodology as well as assessment reliability.

scholarly journals REMOTE SENSING OF WATER BALANCE IN PANTANAL

2019 ◽  
Vol 46 (3) ◽  
pp. 20
Author(s):  
Adriana Aparecida Moreira ◽  
Alice César Fassoni-Andrade ◽  
Anderson Luis Ruhoff ◽  
Rodrigo Cauduro Dias de Paiva
Keyword(s):  
Remote Sensing ◽  
Water Balance ◽  
Water Storage ◽  
Remote Sensing Data ◽  
Northern Region ◽  
Sensing Data ◽  
In Situ Data ◽  
Storage Change ◽  
Hydrological Variables

Pantanal, located in the Upper Paraguay basin, is the world’s largest tropical wetland. The maintenance of this ecosystem depends on the water balance since precipitation is seasonal and high losses of water occur due to the high evapotranspiration. Water balance assessment using in situ data is still a challenge due to the large extension of the area and the complexity to be represented. In this study, the water balance in the Upper Paraguay basin was investigated based on hydrological variables derived from remote sensing data. Precipitation, evapotranspiration, and water storage change data were estimated with accuracy by the water balance, but the same was not possible for the discharge. However, high uncertainties in the estimates were verified, mainly during the rainy season. The remote sensing data allowed the identification of the seasonality of hydrological variables in the Pantanal system and in the different regions of the basin: Chaco, Pantanal and Planalto. Water deficit in the basin was observed from March/April to September as well as a positive water balance due to precipitation during the rest of the year. The spatial analysis of the basin showed that in the northern region, the precipitation, the evapotranspiration, and the water storage variation are higher than in the southern region. Results demonstrated that remote sensing data can help in the comprehension of hydrological systems operation, especially in large wetland regions.

scholarly journals Deep Learning for Monitoring Agricultural Drought in South Asia Using Remote Sensing Data

2021 ◽  
Vol 13 (9) ◽  
pp. 1715
Author(s):  
Foyez Ahmed Prodhan ◽  
Jiahua Zhang ◽  
Fengmei Yao ◽  
Lamei Shi ◽  
Til Prasad Pangali Sharma ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
South Asia ◽  
Model Performance ◽  
Remote Sensing Data ◽  
Agricultural Drought ◽  
Gradient Boosting ◽  
Complex Nature ◽  
Sensing Data

Drought, a climate-related disaster impacting a variety of sectors, poses challenges for millions of people in South Asia. Accurate and complete drought information with a proper monitoring system is very important in revealing the complex nature of drought and its associated factors. In this regard, deep learning is a very promising approach for delineating the non-linear characteristics of drought factors. Therefore, this study aims to monitor drought by employing a deep learning approach with remote sensing data over South Asia from 2001–2016. We considered the precipitation, vegetation, and soil factors for the deep forwarded neural network (DFNN) as model input parameters. The study evaluated agricultural drought using the soil moisture deficit index (SMDI) as a response variable during three crop phenology stages. For a better comparison of deep learning model performance, we adopted two machine learning models, distributed random forest (DRF) and gradient boosting machine (GBM). Results show that the DFNN model outperformed the other two models for SMDI prediction. Furthermore, the results indicated that DFNN captured the drought pattern with high spatial variability across three penology stages. Additionally, the DFNN model showed good stability with its cross-validated data in the training phase, and the estimated SMDI had high correlation coefficient R2 ranges from 0.57~0.90, 0.52~0.94, and 0.49~0.82 during the start of the season (SOS), length of the season (LOS), and end of the season (EOS) respectively. The comparison between inter-annual variability of estimated SMDI and in-situ SPEI (standardized precipitation evapotranspiration index) showed that the estimated SMDI was almost similar to in-situ SPEI. The DFNN model provides comprehensive drought information by producing a consistent spatial distribution of SMDI which establishes the applicability of the DFNN model for drought monitoring.

Sign in / Sign up

Export Citation Format

Share Document