The Soil Moisture Active Passive (SMAP) mission measures important soil moisture data globally. SMAP's products might not always perform better than land surface models (LSM) when evaluated against in situ measurements. However, we hypothesize that SMAP presents added value for long-term soil moisture estimation in a data fusion setting as evaluated by in situ data. Here, with the help of a time series deep learning (DL) method, we created a seamlessly extended SMAP data set to test this hypothesis and, importantly, gauge whether such benefits extend to years beyond SMAP's limited lifespan. We first show that the DL model, called long short-term memory (LSTM), can extrapolate SMAP for several years and the results are similar to the training period. We obtained prolongation results with low-performance degradation where SMAP itself matches well with in situ data. Interannual trends of root-zone soil moisture are surprisingly well captured by LSTM. In some cases, LSTM's performance is limited by SMAP, whose main issue appears to be its shallow sensing depth. Despite this limitation, a simple average between LSTM and an LSM Noah frequently outperforms Noah alone. Moreover, Noah combined with LSTM is more skillful than when it is combined with another LSM. Over sparsely instrumented sites, the Noah-LSTM combination shows a stronger edge. Our results verified the value of LSTM-extended SMAP data. Moreover, DL is completely data driven and does not require structural assumptions. As such, it has its unique potential for long-term projections and may be applied synergistically with other model-data integration techniques.
more »
« less
Evaluating a global soil moisture dataset from a multitask model (GSM3 v1.0) with potential applications for crop threats
Abstract. Climate change threatens our ability to grow food for an ever-increasing population. There is aneed for high-quality soil moisture predictions in under-monitored regionslike Africa. However, it is unclear if soil moisture processes are globallysimilar enough to allow our models trained on available in situ data tomaintain accuracy in unmonitored regions. We present a multitask longshort-term memory (LSTM) model that learns simultaneously from globalsatellite-based data and in situ soil moisture data. This model is evaluated inboth random spatial holdout mode and continental holdout mode (trained onsome continents, tested on a different one). The model compared favorably tocurrent land surface models, satellite products, and a candidate machinelearning model, reaching a global median correlation of 0.792 for the randomspatial holdout test. It behaved surprisingly well in Africa and Australia,showing high correlation even when we excluded their sites from the trainingset, but it performed relatively poorly in Alaska where rapid changes areoccurring. In all but one continent (Asia), the multitask model in theworst-case scenario test performed better than the soil moisture activepassive (SMAP) 9 km product. Factorial analysis has shown that the LSTM model'saccuracy varies with terrain aspect, resulting in lower performance for dryand south-facing slopes or wet and north-facing slopes. This knowledgehelps us apply the model while understanding its limitations. This model isbeing integrated into an operational agricultural assistance applicationwhich currently provides information to 13 million African farmers.
more »
« less
- NSF-PAR ID:
- 10437879
- Date Published:
- Journal Name:
- Geoscientific Model Development
- Volume:
- 16
- Issue:
- 5
- ISSN:
- 1991-9603
- Page Range / eLocation ID:
- 1553 to 1567
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Deep learning (DL) models trained on hydrologic observations can perform extraordinarily well, but they can inherit deficiencies of the training data, such as limited coverage of in situ data or low resolution/accuracy of satellite data. Here we propose a novel multiscale DL scheme learning simultaneously from satellite and in situ data to predict 9 km daily soil moisture (5 cm depth). Based on spatial cross‐validation over sites in the conterminous United States, the multiscale scheme obtained a median correlation of 0.901 and root‐mean‐square error of 0.034 m3/m3. It outperformed the Soil Moisture Active Passive satellite mission's 9 km product, DL models trained on in situ data alone, and land surface models. Our 9 km product showed better accuracy than previous 1 km satellite downscaling products, highlighting limited impacts of improving resolution. Not only is our product useful for planning against floods, droughts, and pests, our scheme is generically applicable to geoscientific domains with data on multiple scales, breaking the confines of individual data sets.
-
more » « less
Abstract We investigated the potential causes of topographic asymmetry at Gabilan Mesa, CA, a site that exhibits large aspect‐dependent differences in hillslope gradients and microclimates. Competing hypotheses have been proposed to explain the asymmetry observed at Gabilan Mesa. One hypothesis states that different microclimates on opposing slopes are responsible for differences in runoff or soil strength, which generates asymmetric topography. A second hypothesis states that differences in sediment flux from opposing slopes causes southward lateral channel migration and oversteepening of north facing slopes. To test these hypotheses, we carried out numerical modeling experiments, terrain analysis, and field measurements. We also considered the role of initial tilting in causing the asymmetry. We found that saturated hydraulic conductivity is considerably lower on south facing slopes in one highly asymmetric basin. This is consistent with the hypothesis that aspect‐dependent runoff is responsible for the asymmetry. We also used cosmogenic radionuclide‐derived erosion rates and topographic characteristics at Gabilan Mesa to test predictions from numerical landscape evolution models that incorporate asymmetry‐forming mechanisms. The aspect‐dependent models reproduce the erosional and topographic characteristics of Gabilan Mesa better than the lateral channel migration model. We conclude that aspect‐dependent runoff is the most likely explanation for most of the topographic asymmetry at Gabilan Mesa. Our results do not rule out tilting as a possible influence on the initial development of asymmetry nor do they rule out the possibility that lateral channel migration has contributed to the asymmetry, but we suggest that tilting and lateral channel migration are not primarily responsible for it.
-
more » « less
Abstract Accurate soil moisture and streamflow data are an aspirational need of many hydrologically relevant fields. Model simulated soil moisture and streamflow hold promise but models require validation prior to application. Calibration methods are commonly used to improve model fidelity but misrepresentation of the true dynamics remains a challenge. In this study, we leverage soil parameter estimates from the Soil Survey Geographic (SSURGO) database and the probability mapping of SSURGO (POLARIS) to improve the representation of hydrologic processes in the Weather Research and Forecasting Hydrological modeling system (WRF‐Hydro) over a central California domain. Our results show WRF‐Hydro soil moisture exhibits increased correlation coefficients (
r ), reduced biases, and increased Kling‐Gupta Efficiencies (KGEs) across seven in situ soil moisture observing stations after updating the model's soil parameters according to POLARIS. Compared to four well‐established soil moisture data sets including Soil Moisture Active Passive data and three Phase 2 North American Land Data Assimilation System land surface models, our POLARIS‐adjusted WRF‐Hydro simulations produce the highest mean KGE (0.69) across the seven stations. More importantly, WRF‐Hydro streamflow fidelity also increases, especially in the case where the model domain is set up with SSURGO‐informed total soil thickness. The magnitude and timing of peak flow events are better captured,r increases across nine United States Geological Survey stream gages, and the mean KGE across seven of the nine gages increases from 0.12 to 0.66. Our pre‐calibration parameter estimate approach, which is transferable to other spatially distributed hydrological models, can substantially improve a model's performance, helping reduce calibration efforts and computational costs. -
Soil temperature and soil moisture have been measured at multiple locations at the Hubbard Brook Experimental Forest (HBEF), as part of a study of the relationships between snow depth, soil freezing and nutrient cycling (http://www.ecostudies.org/people_sci_groffman_snow_summary.html). In October 2010, we established 6, 20 x 20-m plots (intensive plots) and 14 10 x 10-m plots (extensive plots) along an elevation gradient, with eight of the plots on north-facing slopes and twelve on south-facing slopes. Soil temperature and soil moisture were measured at hourly intervals on these plots beginning in November 2010. Six locations were discontinued in September 2012 (E04, E05, E06, E11-B, E13, and E14). Previous versions of this dataset included both temperature and moisture. These data are now available as temperature (this dataset) and moisture (https://portal.edirepository.org/nis/mapbrowse?scope=knb-lter-hbr&identifier=137). These data were gathered as part of the Hubbard Brook Ecosystem Study (HBES). The HBES is a collaborative effort at the Hubbard Brook Experimental Forest, which is operated and maintained by the USDA Forest Service, Northern Research Station.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.5194/gmd-16-1553-2023
