1
|
Wang X, Lü H, Crow WT, Corzo G, Zhu Y, Su J, Zheng J, Gou Q. A reduced latency regional gap-filling method for SMAP using random forest regression. iScience 2022; 26:105853. [PMID: 36619984 PMCID: PMC9817173 DOI: 10.1016/j.isci.2022.105853] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2022] [Revised: 11/09/2022] [Accepted: 12/19/2022] [Indexed: 12/24/2022] Open
Abstract
The soil moisture active/passive (SMAP) mission represents a significant advance in measuring soil moisture from satellites. However, its large spatial-temporal data gaps limit the use of its values in near-real-time (NRT) applications. Considering this, the study uses NRT operational metadata (precipitation and skin temperature), together with some surface parameterization information, to feed into a random forest model to retrieve the missing values of the SMAP L3 soil moisture product. This practice was tested in filling the missing points for both SMAP descending (6:00 AM) and ascending orbits (6:00 PM) in a crop-dominated area from 2015 to 2019. The trained models with optimized hyper-parameters show the goodness of fit (R2 ≥ 0.86), and their resulting gap-filled estimates were compared against a range of competing products with in situ and triple collocation validation. This gap-filling scheme driven by low-latency data sources is first attempted to enhance NRT spatiotemporal support for SMAP L3 soil moisture.
Collapse
Affiliation(s)
- Xiaoyi Wang
- State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, National Cooperative Innovation Center for Water Safety and Hydro-science, College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China,Joint International Research Laboratory of Global Change and Water Cycle, Hohai University, Nanjing 210098, China
| | - Haishen Lü
- State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, National Cooperative Innovation Center for Water Safety and Hydro-science, College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China,Joint International Research Laboratory of Global Change and Water Cycle, Hohai University, Nanjing 210098, China,Corresponding author
| | - Wade T. Crow
- USDA-ARS Hydrology and Remote Sensing Laboratory, Beltsville, MD 20705-2350, USA
| | - Gerald Corzo
- Hydroinformatics Chair Group, IHE Delft Institute for Water Education, 2611AX Delft, the Netherlands
| | - Yonghua Zhu
- State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, National Cooperative Innovation Center for Water Safety and Hydro-science, College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China,Joint International Research Laboratory of Global Change and Water Cycle, Hohai University, Nanjing 210098, China
| | - Jianbin Su
- National Tibetan Plateau Data Center, Key Laboratory of Tibetan Environmental Changes and Land Surface Processes, Institute of Tibetan Plateau Research, Chinese Academy of Sciences, Beijing 100101, China
| | - Jingyao Zheng
- State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, National Cooperative Innovation Center for Water Safety and Hydro-science, College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China,Joint International Research Laboratory of Global Change and Water Cycle, Hohai University, Nanjing 210098, China
| | - Qiqi Gou
- State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, National Cooperative Innovation Center for Water Safety and Hydro-science, College of Hydrology and Water Resources, Hohai University, Nanjing 210098, China,Joint International Research Laboratory of Global Change and Water Cycle, Hohai University, Nanjing 210098, China
| |
Collapse
|
2
|
Zeynoddin M, Bonakdari H. Structural-optimized sequential deep learning methods for surface soil moisture forecasting, case study Quebec, Canada. Neural Comput Appl. [DOI: 10.1007/s00521-022-07529-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/17/2022]
|
3
|
De Cannière S, Vereecken H, Defourny P, Jonard F. Remote Sensing of Instantaneous Drought Stress at Canopy Level Using Sun-Induced Chlorophyll Fluorescence and Canopy Reflectance. Remote Sensing 2022; 14:2642. [DOI: 10.3390/rs14112642] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/04/2023]
Abstract
Climate change amplifies the intensity and occurrence of dry periods leading to drought stress in vegetation. For monitoring vegetation stresses, sun-induced chlorophyll fluorescence (SIF) observations are a potential game-changer, as the SIF emission is mechanistically coupled to photosynthetic activity. Yet, the benefit of SIF for drought stress monitoring is not yet understood. This paper analyses the impact of drought stress on canopy-scale SIF emission and surface reflectance over a lettuce and mustard stand with continuous field spectrometer measurements. Here, the SIF measurements are linked to the plant’s photosynthetic efficiency, whereas the surface reflectance can be used to monitor the canopy structure. The mustard canopy showed a reduction in the biochemical component of its SIF emission (the fluorescence emission efficiency at 760 nm—ϵ760) as a reaction to drought stress, whereas its structural component (the Fluorescence Correction Vegetation Index—FCVI) barely showed a reaction. The lettuce canopy showed both an increase in the variability of its surface reflectance at a sub-daily scale and a decrease in ϵ760 during a drought stress event. These reactions occurred simultaneously, suggesting that sun-induced chlorophyll fluorescence and reflectance-based indices sensitive to the canopy structure provide complementary information. The intensity of these reactions depend on both the soil water availability and the atmospheric water demand. This paper highlights the potential for SIF from the upcoming FLuorescence EXplorer (FLEX) satellite to provide a unique insight on the plant’s water status. At the same time, data on the canopy reflectance with a sub-daily temporal resolution are a promising additional stress indicator for certain species.
Collapse
|
4
|
Almendra-martín L, Martínez-fernández J, González-zamora Á, Benito-verdugo P, Herrero-jiménez CM. Agricultural Drought Trends on the Iberian Peninsula: An Analysis Using Modeled and Reanalysis Soil Moisture Products. Atmosphere 2021; 12:236. [DOI: 10.3390/atmos12020236] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
Drought has a great impact on agriculture and food security, and climate change is increasing its frequency and exacerbating its intensity. Given the enormous interest in studying the recent drought evolution, in this work, agricultural drought trends over the past four decades on the Iberian Peninsula (IP) were analyzed. A trend analysis was performed with soil moisture based on the study of the evolution of anomalies and the Soil Water Deficit Index (SWDI). Two soil moisture databases (Lisflood and ERA5-Land) were used and the analysis was performed at daily and weekly temporal scales. Climate characteristics and soil properties were also considered to detect whether a trend spatial pattern could be identified. The results have shown a clear predominance of negative trends. A marked temporal pattern with negative trends was obtained over a 10-month period that coincided with the growing season of most of the crops on the IP, while a positive trend was observed over 2 months. No differences were found based on the climatic zone or soil characteristics. However, negative trends were observed to decrease as the clay content increased. These results can provide useful information for better water management and agriculture of the IP and other Mediterranean areas.
Collapse
|
5
|
Souissi R, Al Bitar A, Zribi M. Accuracy and Transferability of Artificial Neural Networks in Predicting in Situ Root-Zone Soil Moisture for Various Regions across the Globe. Water 2020; 12:3109. [DOI: 10.3390/w12113109] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
This paper explores the accuracy in using an artificial neural network (ANN) to estimate root-zone soil moisture (RZSM) at multiple worldwide locations using only in situ surface soil moisture (SSM) as a training dataset. The paper also addresses the transferability of the trained ANN across climatic and soil texture conditions. Data from the International Soil Moisture Network (ISMN) were collected for several networks with variable soil texture and climate classes. Several scaling, feature extraction, and training approaches were tested. An artificial neural network employing rolling averages (ANNRAV) of SSM over 10, 30, and 90 days was developed. The results show that applying a standard scaling (SSCA) to the ANN input features improves the correlation, Nash–Sutcliffe efficiency (NSE), and root mean square error (RMSE) for 52%, 91%, and 87%, respectively, of the tested stations, compared to MinMax scaling (MMSCA). Different training sets are suggested, namely, training on data from all networks, data from one network, or data of all networks excluding one. Based on these trainings, new transferability (TranI) and contribution (ContI) indices are defined. The results show that one network cannot provide the best prediction accuracy if used alone to train the ANN. They also show that the removal of the less contributing networks enhances performance. For example, elimination of the densest network (SCAN) from the training enhances the mean correlation by 20.5% and the mean NSE by 42.5%. This motivates the implementation of a data filtering technique based on the ANN’s performance. A median, max, and min correlation of 0.77, 0.96, and 0.65, respectively, are obtained by the model after data filtering. The performances are also analyzed with respect to the covered climatic regions and soil texture, providing insights into the robustness and limitations of the approach, namely, the need for complementary information in highly evaporative regions. In fact, the ANN using only SSM to predict RZSM has low performance when decoupling between the surface and root zones is observed. The application of ANN to obtain spatialized RZSM will require integrating remote sensing-based surface soil moisture in the future.
Collapse
|
6
|
Sazib N, Bolten J, Mladenova I. Exploring Spatiotemporal Relations between Soil Moisture, Precipitation, and Streamflow for a Large Set of Watersheds Using Google Earth Engine. Water 2020; 12:1371. [DOI: 10.3390/w12051371] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
An understanding of streamflow variability and its response to changes in climate conditions is essential for water resource planning and management practices that will help to mitigate the impacts of extreme events such as floods and droughts on agriculture and other human activities. This study investigated the relationship between precipitation, soil moisture, and streamflow over a wide range of watersheds across the United States using Google Earth Engine (GEE). The correlation analyses disclosed a strong association between precipitation, soil moisture, and streamflow, however, soil moisture was found to have a higher correlation with the streamflow relative to precipitation. Results indicated different strength of the association depends on the watershed classes and lag times assessments. The perennial watersheds showed higher coherence compared to intermittent watersheds. Previous month precipitation and soil moisture have a stronger influence on the current month streamflow, particularly in the snow-dominated watersheds. Monthly streamflow forecasting models were developed using an autoregressive integrated moving average (ARIMA) and support vector machine (SVM). The results showed that the SVM model generally performed better than the ARIMA model. Overall streamflow forecasting model performance varied considerably among watershed classes, and perennial watersheds tend to exhibit better predictably compared to intermittent watersheds due to lower streamflow variability. The SVM models with precipitation and streamflow inputs performed better than those with streamflow input only. Results indicated that the inclusion of antecedent root-zone soil moisture improved the streamflow forecasting in most of the watersheds, and the largest improvements occurred in the intermittent watersheds. In conclusion, this work demonstrated that knowing the relationship between precipitation, soil moisture, and streamflow in different watershed classes will enhance the understanding of the hydrologic process and can be effectively utilized in improving streamflow forecasting for better satellite-based water resource management strategies.
Collapse
|