Search for: All records

The loss of phosphorous (P) from the land to aquatic systems has polluted waters and threatened food production worldwide. Systematic trend analysis of P, a nonrenewable resource, has been challenging, primarily due to sparse and inconsistent historical data. Here, we leveraged intensive hydrometeorological data and the recent renaissance of deep learning approaches to fill data gaps and reconstruct temporal trends. We trained a multitask long short-term memory model for total P (TP) using data from 430 rivers across the contiguous United States (CONUS). Trend analysis of reconstructed daily records (1980–2019) shows widespread decline in concentrations, with declining, increasing, and insignificantly changing trends in 60%, 28%, and 12% of the rivers, respectively. Concentrations in urban rivers have declined the most despite rising urban population in the past decades; concentrations in agricultural rivers however have mostly increased, suggesting not-as-effective controls of nonpoint sources in agriculture lands compared to point sources in cities. TP loss, calculated as fluxes by multiplying concentration and discharge, however exhibited an overall increasing rate of 6.5% per decade at the CONUS scale over the past 40 y, largely due to increasing river discharge. Results highlight the challenge of reducing TP loss that is complicated by changing river discharge in a warming climate. 

For a number of years since their introduction to hydrology, recurrent neural networks like long short-term memory (LSTM) networks have proven remarkably difficult to surpass in terms of daily hydrograph metrics on community-shared benchmarks. Outside of hydrology, Transformers have now become the model of choice for sequential prediction tasks, making it a curious architecture to investigate for application to hydrology. Here, we first show that a vanilla (basic) Transformer architecture is not competitive against LSTM on the widely benchmarked CAMELS streamflow dataset, and lagged especially prominently for the high-flow metrics, perhaps due to the lack of memory mechanisms. However, a recurrence-free variant of the Transformer model can obtain mixed comparisons with LSTM, producing very slightly higher Kling-Gupta efficiency coefficients (KGE), along with other metrics. The lack of advantages for the vanilla Transformer network is linked to the nature of hydrologic processes. Additionally, similar to LSTM, the Transformer can also merge multiple meteorological forcing datasets to improve model performance. Therefore, the modified Transformer represents a rare competitive architecture to LSTM in rigorous benchmarks. Valuable lessons were learned: (1) the basic Transformer architecture is not suitable for hydrologic modeling; (2) the recurrence-free modification is beneficial so future work should continue to test such modifications; and (3) the performance of state-of-the-art models may be close to the prediction limits of the dataset. As a non-recurrent model, the Transformer may bear scale advantages for learning from bigger datasets and storing knowledge. This work lays the groundwork for future explorations into pretraining models, serving as a foundational benchmark that underscores the potential benefits in hydrology. 

Accurate hydrologic modeling is vital to characterizing how the terrestrial water cycle responds to climate change. Pure deep learning (DL) models have been shown to outperform process-based ones while remaining difficult to interpret. More recently, differentiable physics-informed machine learning models with a physical backbone can systematically integrate physical equations and DL, predicting untrained variables and processes with high performance. However, it is unclear if such models are competitive for global-scale applications with a simple backbone. Therefore, we use – for the first time at this scale – differentiable hydrologic models (full name δHBV-globe1.0-hydroDL, shortened to δHBV here) to simulate the rainfall–runoff processes for 3753 basins around the world. Moreover, we compare the δHBV models to a purely data-driven long short-term memory (LSTM) model to examine their strengths and limitations. Both LSTM and the δHBV models provide competitive daily hydrologic simulation capabilities in global basins, with median Kling–Gupta efficiency values close to or higher than 0.7 (and 0.78 with LSTM for a subset of 1675 basins with long-term discharge records), significantly outperforming traditional models. Moreover, regionalized differentiable models demonstrated stronger spatial generalization ability (median KGE 0.64) than a traditional parameter regionalization approach (median KGE 0.46) and even LSTM for ungauged region tests across continents. Nevertheless, relative to LSTM, the differentiable model was hampered by structural deficiencies for cold or polar regions, highly arid regions, and basins with significant human impacts. This study also sets the benchmark for hydrologic estimates around the world and builds a foundation for improving global hydrologic simulations. 

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. 

Abstract. Photosynthesis plays an important role in carbon,nitrogen, and water cycles. Ecosystem models for photosynthesis arecharacterized by many parameters that are obtained from limited in situmeasurements and applied to the same plant types. Previous site-by-sitecalibration approaches could not leverage big data and faced issues likeoverfitting or parameter non-uniqueness. Here we developed an end-to-endprogrammatically differentiable (meaning gradients of outputs to variablesused in the model can be obtained efficiently and accurately) version of thephotosynthesis process representation within the Functionally AssembledTerrestrial Ecosystem Simulator (FATES) model. As a genre ofphysics-informed machine learning (ML), differentiable models couplephysics-based formulations to neural networks (NNs) that learn parameterizations(and potentially processes) from observations, here photosynthesis rates. Wefirst demonstrated that the framework was able to correctly recover multiple assumedparameter values concurrently using synthetic training data. Then, using areal-world dataset consisting of many different plant functional types (PFTs), welearned parameters that performed substantially better and greatly reducedbiases compared to literature values. Further, the framework allowed us togain insights at a large scale. Our results showed that the carboxylationrate at 25 ∘C (Vc,max25) was more impactful than a factorrepresenting water limitation, although tuning both was helpful inaddressing biases with the default values. This framework could potentiallyenable substantial improvement in our capability to learn parameters andreduce biases for ecosystem modeling at large scales. 

Abstract The behaviors and skills of models in many geosciences (e.g., hydrology and ecosystem sciences) strongly depend on spatially-varying parameters that need calibration. A well-calibrated model can reasonably propagate information from observations to unobserved variables via model physics, but traditional calibration is highly inefficient and results in non-unique solutions. Here we propose a novel differentiable parameter learning (dPL) framework that efficiently learns a global mapping between inputs (and optionally responses) and parameters. Crucially, dPL exhibits beneficial scaling curves not previously demonstrated to geoscientists: as training data increases, dPL achieves better performance, more physical coherence, and better generalizability (across space and uncalibrated variables), all with orders-of-magnitude lower computational cost. We demonstrate examples that learned from soil moisture and streamflow, where dPL drastically outperformed existing evolutionary and regionalization methods, or required only ~12.5% of the training data to achieve similar performance. The generic scheme promotes the integration of deep learning and process-based models, without mandating reimplementation. 

Abstract Predictions of hydrologic variables across the entire water cycle have significant value for water resources management as well as downstream applications such as ecosystem and water quality modeling. Recently, purely data‐driven deep learning models like long short‐term memory (LSTM) showed seemingly insurmountable performance in modeling rainfall runoff and other geoscientific variables, yet they cannot predict untrained physical variables and remain challenging to interpret. Here, we show that differentiable, learnable, process‐based models (calledδmodels here) can approach the performance level of LSTM for the intensively observed variable (streamflow) with regionalized parameterization. We use a simple hydrologic model HBV as the backbone and use embedded neural networks, which can only be trained in a differentiable programming framework, to parameterize, enhance, or replace the process‐based model's modules. Without using an ensemble or post‐processor,δmodels can obtain a median Nash‐Sutcliffe efficiency of 0.732 for 671 basins across the USA for the Daymet forcing data set, compared to 0.748 from a state‐of‐the‐art LSTM model with the same setup. For another forcing data set, the difference is even smaller: 0.715 versus 0.722. Meanwhile, the resulting learnable process‐based models can output a full set of untrained variables, for example, soil and groundwater storage, snowpack, evapotranspiration, and baseflow, and can later be constrained by their observations. Both simulated evapotranspiration and fraction of discharge from baseflow agreed decently with alternative estimates. The general framework can work with models with various process complexity and opens up the path for learning physics from big data.