Search

Climate change threatens our ability to grow food for an ever-increasing population. There is a need for high-quality soil moisture predictions in under-monitored regions like Africa. However, it is unclear if soil moisture processes are globally similar enough to allow our models trained on available in situ data to maintain accuracy in unmonitored regions. We present a multitask long short-term memory (LSTM) model that learns simultaneously from global satellite-based data and in situ soil moisture data. This model is evaluated in both random spatial holdout mode and continental holdout mode (trained on some continents, tested on a different one). The model compared favorably to current land surface models, satellite products, and a candidate machine learning model, reaching a global median correlation of 0.792 for the random spatial holdout test. It behaved surprisingly well in Africa and Australia, showing high correlation even when we excluded their sites from the training set, but it performed relatively poorly in Alaska where rapid changes are occurring. In all but one continent (Asia), the multitask model in the worst-case scenario test performed better than the soil moisture active passive (SMAP) 9 km product. Factorial analysis has shown that the LSTM model's accuracy varies with terrain aspect, resulting in lower performance for dry and south-facing slopes or wet and north-facing slopes. This knowledge helps us apply the model while understanding its limitations. This model is being integrated into an operational agricultural assistance application which currently provides information to 13 million African farmers.

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., Much effort is invested in calibrating model parameters for accurate outputs, but established methods can be inefficient and generic. By learning from big dataset, a new differentiable framework for model parameterization outperforms state-of-the-art methods, produce more physically-coherent results, using a fraction of the training data, computational power, and time. The method promotes a deep integration of machine learning with process-based geoscientific models.

Climate change threatens our ability to grow food for a growing population. There are concurrent droughts and floods happening globally, with the greatest impacts felt in Africa. There is a need for high-quality soil moisture predictions in under-monitored regions like Africa. Yet it is unclear if soil moisture processes are globally similar enough to allow our models to maintain accuracy in unmonitored regions. We present a multitask long short-term memory (LSTM) model that learns simultaneously from global satellite-based and in-situ soil moisture data. This model is evaluated in both random spatial holdout mode and continental holdout mode (trained on some continents, tested on a different one). The model compared favorably to current land surface models, satellite products, and a candidate machine learning model, reaching a global median correlation of 0.792 for the random spatial holdout test. It behaved surprisingly well in Africa and Australia, showing high correlation even when we excluded their sites from the training set, but performed relatively poorly in Alaska where rapid changes are occurring. In all but one continent (Asia), the multitask model in the worst-case scenario test performed better than the soil moisture active passive (SMAP) 9-km product. Factorial analysis shows that the LSTM model’s accuracy with representing impacts of terrain aspect, resulting in lower performance for dry and south-facing slopes or wet and north-facing slopes. This knowledge helps us apply the model while understanding its limitations. This model is being integrated into an operational agricultural assistance application which currently provides information to 13 million African farmers.

This article explores an alternative autoethnographic methodological approach, using embodied praxis and sound, for critically re-thinking contemporary subjective health practices of digital ‘self-tracking’; popularized in recent years through the rise in wearable biometric fitness devices, and online socio-cultural movements such as the Quantified Self and Strava platforms, which enable subjects to “share” their quantifiable body-data metrics. Through a performative praxis case study titled Speaking the Data (2017), the author renegotiates the “voice” of subjective agency within the quantitative data-discourse, “speaking the data” that her body is producing in “real-time” on a digital smart-bike machine. This embodied renegotiation, recorded using a sound “data-stream,” produces an alternative subjective data-set which is extended to the reader, who is invited to become “listener” in the theoretical/experiential praxis space. The sound “data-stream” thus proffers an affective expansion to our perceptions of what “body-data” can be, extending the possibilities for the digitally mediated body beyond biometric forms of quantification, through other sensorial registers of embodiment, using sound, rhythmic affect and lived experience.

Differentiable, learnable process-based hydrologic models (abbreviated as δ or delta models) with regionalized parameterization pipelines were recently shown to provide daily streamflow prediction performance that closely approach state-of-the-art long short-term memory (LSTM) deep networks. Meanwhile, δ models provide a full suite of diagnostic physical variables and guaranteed mass conservation. Due to their physical constraints, we hypothesize that they are suitable for making extrapolated predictions. Here, we ran experiments to test (1) their ability to extrapolate to regions far from streamflow gauges; and (2) their ability to make credible projections of long-term (decadal-scale) change trends. We evaluate the models based on daily hydrograph metrics (Nash-Sutcliffe model efficiency coefficient, etc.), as well as projected decadal streamflow trends. The results show that, for spatial interpolation (test in randomly sampled ungauged basins, or PUB), δ models have mixed comparisons with LSTM, presenting better trends for annual mean flow and high flow but slightly worse for low flow. For spatial extrapolation (test in regionally held out basins, or PUR, representing a highly data-scarce scenario), δ models’ advantages in mean and high flows are more prominent. In addition, an untrained variable, evapotranspiration, retained good seasonality even for extrapolated cases. δ models’ parameterization pipeline produces parameter fields that maintain remarkably stable spatial patterns even in highly data-scarce scenarios, which explains their robustness. Combined with their interpretability and ability to assimilate multi-source observations, δ models are strong candidates for regional and global scale hydrologic simulations for climate change impact assessment.

When fitting statistical models to variables in geoscientific disciplines such as hydrology, it is a customary practice to regionalize - to divide a large spatial domain into multiple regions and study each region separately - instead of fitting a single model on the entire data (also known as unification). Traditional wisdom in these fields suggests that models built for each region separately will have higher performance because of homogeneity within each region. However, by partitioning the training data, each model has access to fewer data points and cannot learn from commonalities between regions. Here, through two hydrologic examples (soil moisture and streamflow), we argue that unification can often significantly outperform regionalization in the era of big data and deep learning (DL). Common DL architectures, even without bespoke customization, can automatically build models that benefit from regional commonality while accurately learning region-specific differences. We highlight an effect we call data synergy, where the results of the DL models improved when data were pooled together from characteristically different regions. In fact, the performance of the DL models benefited from more diverse rather than more homogeneous training data. We hypothesize that DL models automatically adjust their internal representations to identify commonalities while also providing sufficient discriminatory information to the model. The results here advocate for pooling together larger datasets, and suggest the academic community should place greater emphasis on data sharing and compilation.

In this article, we consider the scenario where remotely sensed images are collected sequentially in temporal batches, where each batch focuses on images from a particular ecoregion, but different batches can focus on different ecoregions with distinct landscape characteristics. For such a scenario, we study the following questions: (1) How well do DL models trained in homogeneous regions perform when they are transferred to different ecoregions, (2) Does increasing the spatial coverage in the data improve model performance in a given ecoregion (even when the extra data do not come from the ecoregion), and (3) Can a landslide pixel labelling model be incrementally updated with new data, but without access to the old data and without losing performance on the old data (so that researchers can share models obtained from proprietary datasets)? We address these questions by a framework called Task-Specific Model Updates (TSMU). The goal of this framework is to continually update a (landslide) semantic segmentation model with data from new ecoregions without having to revisit data from old ecoregions and without losing performance on them. We conduct extensive experiments on four ecoregions in the United States to address the above questions and establish that data from other ecoregions can help improve the model's performance on the original ecoregion. In other words, if one has an ecoregion of interest, one could still collect data both inside and outside that region to improve model performance on the ecoregion of interest. Furthermore, if one has many ecoregions of interest, data from all of them are needed.

Predictions of hydrologic variables across the entire water cycle have significant value for water resource 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 (called {\delta} models 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 modules. Without using an ensemble or post-processor, {\delta} models can obtain a median Nash Sutcliffe efficiency of 0.732 for 671 basins across the USA for the Daymet forcing dataset, compared to 0.748 from a state-of-the-art LSTM model with the same setup. For another forcing dataset, the difference is even smaller: 0.715 vs. 0.722. Meanwhile, the resulting learnable process-based models can output a full set of untrained variables, e.g., soil and groundwater storage, snowpack, evapotranspiration, and baseflow, and 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.

Hydroelectric power (hydropower) is unique in that it can function as both a conventional source of electricity and as backup storage (pumped hydroelectric storage and large reservoir storage) for providing energy in times of high demand on the grid (S. Rehman, L M Al-Hadhrami, and M M Alam), (2015 Renewable and Sustainable Energy Reviews, 44, 586–98). This study examines the impact of hydropower on system electricity price and price volatility in the region served by the New England Independent System Operator (ISONE) from 2014-2020 (ISONE, ISO New England Web Services API v1.1.” https://webservices.iso-ne.com/docs/v1.1/, 2021. Accessed: 2021-01-10). We perform a robust holistic analysis of the mean and quantile effects, as well as the marginal contributing effects of hydropower in the presence of solar and wind resources. First, the price data is adjusted for deterministic temporal trends, correcting for seasonal, weekend, and diurnal effects that may obscure actual representative trends in the data. Using multiple linear regression and quantile regression, we observe that hydropower contributes to a reduction in the system electricity price and price volatility. While hydropower has a weak impact on decreasing price and volatility at the mean, it has greater impact at extreme quantiles (>70th percentile). At these higher percentiles, we find that hydropower provides a stabilizing effect on price volatility in the presence of volatile resources such as wind. We conclude with a discussion of the observed relationship between hydropower and system electricity price and volatility.

Basin-centric long short-term memory (LSTM) network models have recently been shown to be an exceptionally powerful tool for simulating stream temperature (Ts, temperature measured in rivers), among other hydrological variables. However, spatial extrapolation is a well-known challenge to modeling Ts and it is uncertain how an LSTM-based daily Ts model will perform in unmonitored or dammed basins. Here we compiled a new benchmark dataset consisting of >400 basins for across the contiguous United States in different data availability groups (DAG, meaning the daily sampling frequency) with or without major dams and study how to assemble suitable training datasets for predictions in monitored or unmonitored situations. For temporal generalization, CONUS-median best root-mean-square error (RMSE) values for sites with extensive (99%), intermediate (60%), scarce (10%) and absent (0%, unmonitored) data for training were 0.75, 0.83, 0.88, and 1.59°C, representing the state of the art. For prediction in unmonitored basins (PUB), LSTM’s results surpassed those reported in the literature. Even for unmonitored basins with major reservoirs, we obtained a median RMSE of 1.492°C and an R2 of 0.966. The most suitable training set was the matching DAG that the basin could be grouped into, e.g., the 60% DAG for a basin with 61% data availability. However, for PUB, a training dataset including all basins with data is preferred. An input-selection ensemble moderately mitigated attribute overfitting. Our results suggest there are influential latent processes not sufficiently described by the inputs (e.g., geology, wetland covers), but temporal fluctuations are well predictable, and LSTM appears to be the more accurate Ts modeling tool when sufficient training data are available.

Counterfeit medicines represent a global public health threat warranting the development of accurate, rapid, and nondestructive methods for their identification. Portable near-infrared (NIR) spectroscopy offers this advantage. This work sheds light on the potential of combining NIR spectroscopy with principal component analysis (PCA) and soft independent modelling of class analogy (SIMCA) for authenticating branded and generic antibiotics. A total of 23 antibiotics were measured “nondestructively” using a portable NIR spectrometer. The antibiotics corresponded to six different active pharmaceutical ingredients being: amoxicillin trihydrate and clavulanic acid, azithromycin dihydrate, ciprofloxacin hydrochloride, doxycycline hydrochloride, and ofloxacin. NIR spectra were exported into Matlab R2018b where data analysis was applied. The results showed that the NIR spectra of the medicines showed characteristic features that corresponded to the main excipient(s). When combined with PCA, NIR spectroscopy could distinguish between branded and generic medicines and could classify medicines according to their manufacturing sources. The PCA scores showed the distinct clusters corresponding to each group of antibiotics, whereas the loadings indicated which spectral features were significant. SIMCA provided more accurate classification over PCA for all antibiotics except ciprofloxacin which products shared many overlapping excipients. In summary, the findings of the study demonstrated the feasibility of portable NIR as an initial method for screening antibiotics.

A large fraction of major waterways have dams influencing streamflow, which must be accounted for in large-scale hydrologic modeling. However, daily streamflow prediction for basins with dams is challenging for various modeling approaches, especially at large scales. Here we examined which types of dammed basins could be well represented by long short-term memory (LSTM) models using readily-available information, and delineated the remaining challenges. We analyzed data from 3557 basins (83% dammed) over the contiguous United States and noted strong impacts of reservoir purposes, degree of regulation (dor), and diversion on streamflow modeling. While a model trained on a widely-used reference-basin dataset performed poorly for non-reference basins, the model trained on the whole dataset presented a median Nash-Sutcliffe efficiency coefficient (NSE) of 0.74. The zero-dor, small-dor (with storage of approximately a month of average streamflow or less), and large-dor basins were found to have distinct behaviors, so migrating models between categories yielded catastrophic results, which means we must not treat small-dor basins as reference ones. However, training with pooled data from different sets yielded optimal median NSEs of 0.72, 0.79, and 0.64 for these respective groups, noticeably stronger than existing models. These results support a coherent modeling strategy where smaller dams (storing about a month of average streamflow or less) are modeled implicitly as part of basin rainfall-runoff processes; then, large-dor reservoirs of certain types can be represented explicitly. However, dammed basins must be present in the training dataset. Future work should examine separate modeling of large reservoirs for fire protection and irrigation, hydroelectric power generation, and flood control.

Stream water temperature (T) is a variable of critical importance and decision-making relevance to aquatic ecosystems, energy production, and human’s interaction with the river system. Here, we pro...

Recently, recurrent deep networks have shown promise to harness newly available satellite-sensed data for long-term soil moisture projections. However, to be useful in forecasting, deep networks mu...

Some regions of Argentina are affected by high concentrations of molybdenum, arsenic and vanadium from natural sources in their groundwater. In particular, Mo levels in groundwater from Eduardo Castex (La Pampa, Argentina) typically exceed the guidelines for drinking water formerly established by WHO at 70 μg/L. Therefore, this study investigated the uptake of Mo in plants, using cress (Lepidium sativum L.) as a model using hydroponic experiments with synthetic solutions and groundwater from La Pampa. Cress grown from control experiments (150 μg/L Mo, pH 7) presented an average Mo concentration of 35.2 mg/kg (dry weight, d.w.), higher than the typical total plant range (0.7–2.5 mg/kg d.w.) in the literature. Using pooled groundwater samples (65.0–92.5 μg/L Mo) from wells of La Pampa (Argentina) as growth solutions resulted in significantly lower cress Mo levels (1.89–4.59 mg/kg d.w.) than were obtained for synthetic solutions of equivalent Mo concentration. This may be due to the high levels in these groundwater samples of As, V, Fe and Mn which are known to be associated with volcanic deposits. This research addressed the hitherto scarcity of data about the effect of various physicochemical parameters on the uptake of Mo in plants. Supplementary Information The online version contains supplementary material available at 10.1007/s11356-021-13902-w.

A review of the literature relating to plagiarism suggests that there is substantial variability in approach between institutions. Some institutions tend to view all occurrences of plagiarism as academic misconduct, whilst others take a more graded view – articulated through policy and procedures that aim to quantify 'levels' of severity. Measured approaches such as these tend to rely on guides to help assess the level of severity, typically encompassing the experience of the student, the amount of material plagiarised, and the likelihood of an intention to deceive. Such judgements lead to a graded response to the student which can result in a wide range of outcomes, from educational guidance and support to expulsion from the institution. However, the intent to deceive can be extremely difficult to establish. This paper will draw on a desktop study of institutional policies and procedures in Australia and other countries to sample and summarise the myriad approaches to the definition and determination of (specifically) intent in plagiarism. Based on the findings of this review, we suggest that the treatment of intent is, at best, rather inconsistent. A series of 'probability factors' are proposed to guide further research in this area.