WaterBench: A Large-scale Benchmark Dataset for Data-Driven Streamflow Forecasting

This study proposes a comprehensive benchmark dataset for streamflow forecasting, WaterBench, that follows FAIR data principles that is prepared with a focus on convenience for utilizing in data-driven and machine learning studies, and provides benchmark performance for state-of-art deep learning architectures on the dataset for comparative analysis. By aggregating the datasets of streamflow, precipitation, watershed area, slope, soil types, and evapotranspiration from federal agencies and state organizations (i.e., NASA, NOAA, USGS, and Iowa Flood Center), we provided the WaterBench for hourly streamflow forecast studies. This dataset has a high temporal and spatial resolution with rich metadata and relational information, which can be used for varieties of deep learning and machine learning research. We defined a sample streamflow forecasting task for the next 120 hours and provided performance benchmarks on this task with sample linear regression and deep learning models, including Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and S2S (Sequence-to-sequence). To some extent, WaterBench makes up for the lack of a unified benchmark in earth science research. We highly encourage researchers to use the WaterBench for deep learning research in hydrology.

Download Full-text

The performance of LSTM models from basin to continental scales

10.5194/egusphere-egu2020-8855 ◽

2020 ◽

Author(s):

Frederik Kratzert ◽

Daniel Klotz ◽

Günter Klambauer ◽

Grey Nearing ◽

Sepp Hochreiter

Keyword(s):

Machine Learning ◽

Large Scale ◽

Short Term Memory ◽

Regional Scale ◽

Data Driven ◽

Hydrological Models ◽

Short Term ◽

Term Memory ◽

Basin Scale ◽

Long Short Term Memory

Simulation accuracy among traditional hydrological models usually degrades significantly when going from single basin to regional scale. Hydrological models perform best when calibrated for specific basins, and do worse when a regional calibration scheme is used.&#160;One reason for this is that these models do not (have to) learn hydrological processes from data. Rather, they have a predefined model structure and only a handful of parameters adapt to specific basins. This often yields less-than-optimal parameter values when the loss is not determined by a single basin, but by many through regional calibration.The opposite is true for data driven approaches where models tend to get better with more and diverse training data. We examine whether this holds true when modeling rainfall-runoff processes with deep learning, or if, like their process-based counterparts, data-driven hydrological models degrade when going from basin to regional scale.Recently, Kratzert et al. (2018) showed that the Long Short-Term Memory network (LSTM), a special type of recurrent neural network, achieves comparable performance to the SAC-SMA at basin scale. In follow up work Kratzert et al. (2019a) trained a single LSTM for hundreds of basins in the continental US, which outperformed a set of hydrological models significantly, even compared to basin-calibrated hydrological models. On average, a single LSTM is even better in out-of-sample predictions (ungauged) compared to the SAC-SMA in-sample (gauged) or US National Water Model (Kratzert et al. 2019b).LSTM-based approaches usually involve tuning a large number of hyperparameters, such as the number of neurons, number of layers, and learning rate, that are critical for the predictive performance. Therefore, large-scale hyperparameter search has to be performed to obtain a proficient LSTM network.&#160;&#160;However, in the abovementioned studies, hyperparameter optimization was not conducted at large scale and e.g. in Kratzert et al. (2018) the same network hyperparameters were used in all basins, instead of tuning hyperparameters for each basin separately. It is yet unclear whether LSTMs follow the same trend of traditional hydrological models to degrade performance from basin to regional scale.&#160;In the current study, we performed a computational expensive, basin-specific hyperparameter search to explore how site-specific LSTMs differ in performance compared to regionally calibrated LSTMs. We compared our results to the mHM and VIC models, once calibrated per-basin and once using an MPR regionalization scheme. These benchmark models were calibrated individual research groups, to eliminate bias in our study. We analyse whether differences in basin-specific vs regional model performance can be linked to basin attributes or data set characteristics.References:Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M.: Rainfall&#8211;runoff modelling using Long Short-Term Memory (LSTM) networks, Hydrol. Earth Syst. Sci., 22, 6005&#8211;6022, https://doi.org/10.5194/hess-22-6005-2018, 2018.&#160;Kratzert, F., Klotz, D., Shalev, G., Klambauer, G., Hochreiter, S., and Nearing, G.: Towards learning universal, regional, and local hydrological behaviors via machine learning applied to large-sample datasets, Hydrol. Earth Syst. Sci., 23, 5089&#8211;5110, https://doi.org/10.5194/hess-23-5089-2019, 2019a.&#160;Kratzert, F., Klotz, D., Herrnegger, M., Sampson, A. K., Hochreiter, S., & Nearing, G. S.: Toward improved predictions in ungauged basins: Exploiting the power of machine learning. Water Resources Research, 55. https://doi.org/10.1029/2019WR026065, 2019b.

Download Full-text

Earth science phenomena portal: from deep learning-based event detection to visual exploration

10.5194/egusphere-egu2020-10435 ◽

2020 ◽

Author(s):

Manil Maskey ◽

Rahul Ramachandran ◽

Iksha Gurung ◽

Muthukumaran Ramasubramanian ◽

Aaron Kaulfus ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Feature Detection ◽

Earth Science ◽

Machine Learning Algorithms ◽

Visual Exploration ◽

Data Driven ◽

Production Environment ◽

Learning Models ◽

Data Search

Earth science researchers typically use event (an instance of an Earth science phenomenon) data for case study analysis. However, Earth science data search systems are currently limited to specifying a query parameter that includes the space and time of an event.&#160; Such an approach results in researchers spending a considerable amount of time sorting through data to conduct research studies on events.&#160; With the growing data volumes, it is imperative to investigate data-driven approaches to address this limitation in the data search system.We describe several contributions towards alternative ways to accelerate event-based studies from large data archives.&#160;The first contribution is the use of a machine learning-based approach, an enabling data-driven technology, to detect Earth science events from image archives.&#160; Specifically, the development of deep learning models to detect various Earth science phenomena is discussed.&#160; Deep learning includes machine learning algorithms that consist of multiple layers, where each layer performs feature detection.&#160;&#160; We leverage recent advancements in deep learning techniques (mostly using convolutional neural networks (CNNs) that have produced state-of-the-art image classification results in many domains.The second contribution is the development of an event database and a phenomena portal.&#160; The phenomena portal utilizes the deep learning detected events cataloged in an event database.&#160; The portal provides a user interface with several features including display of events of the day, spatio-temporal characteristics of events, and integration of user feedback.The third contribution is the development of a cloud-native framework to automate and scale the deep learning models in a production environment.The paper also discusses the challenges in developing an end-to-end Earth science machine learning project and possible approaches to address those challenges.

Download Full-text

Artificial Intelligence & Machine Learning in Computer Vision Applications

Embedded Selforganising Systems ◽

10.14464/ess71432 ◽

2020 ◽

Vol 7 (1) ◽

pp. 2-3

Author(s):

Shadi Saleh

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Neural Networks ◽

Computer Vision ◽

Deep Learning ◽

Large Scale ◽

Short Term Memory ◽

Graphics Processing Unit ◽

Multimedia Data ◽

Processing Unit

Deep learning and machine learning innovations are at the core of the ongoing revolution in Artificial Intelligence for the interpretation and analysis of multimedia data. The convergence of large-scale datasets and more affordable Graphics Processing Unit (GPU) hardware has enabled the development of neural networks for data analysis problems that were previously handled by traditional handcrafted features. Several deep learning architectures such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short Term Memory (LSTM)/Gated Recurrent Unit (GRU), Deep Believe Networks (DBN), and Deep Stacking Networks (DSNs) have been used with new open source software and libraries options to shape an entirely new scenario in computer vision processing.

Download Full-text

Global soil moisture data derived through machine learning trained with in-situ measurements

Scientific Data ◽

10.1038/s41597-021-00964-1 ◽

2021 ◽

Vol 8 (1) ◽

Author(s):

Sungmin O. ◽

Rene Orth

Keyword(s):

Machine Learning ◽

Soil Moisture ◽

Large Scale ◽

Short Term Memory ◽

Temporal Dynamics ◽

Soil Moisture Data ◽

Wide Range ◽

Global Soil

AbstractWhile soil moisture information is essential for a wide range of hydrologic and climate applications, spatially-continuous soil moisture data is only available from satellite observations or model simulations. Here we present a global, long-term dataset of soil moisture derived through machine learning trained with in-situ measurements, SoMo.ml. We train a Long Short-Term Memory (LSTM) model to extrapolate daily soil moisture dynamics in space and in time, based on in-situ data collected from more than 1,000 stations across the globe. SoMo.ml provides multi-layer soil moisture data (0–10 cm, 10–30 cm, and 30–50 cm) at 0.25° spatial and daily temporal resolution over the period 2000–2019. The performance of the resulting dataset is evaluated through cross validation and inter-comparison with existing soil moisture datasets. SoMo.ml performs especially well in terms of temporal dynamics, making it particularly useful for applications requiring time-varying soil moisture, such as anomaly detection and memory analyses. SoMo.ml complements the existing suite of modelled and satellite-based datasets given its distinct derivation, to support large-scale hydrological, meteorological, and ecological analyses.

Download Full-text

Automated Data-Driven Generation of Personalized Pedagogical Interventions in Intelligent Tutoring Systems

International Journal of Artificial Intelligence in Education ◽

10.1007/s40593-021-00267-x ◽

2021 ◽

Author(s):

Ekaterina Kochmar ◽

Dung Do Vu ◽

Robert Belfer ◽

Varun Gupta ◽

Iulian Vlad Serban ◽

...

Keyword(s):

Machine Learning ◽

Student Performance ◽

Language Processing ◽

Intelligent Tutoring Systems ◽

Large Scale ◽

Intelligent Tutoring ◽

Performance Outcomes ◽

Data Driven ◽

Personalized Feedback ◽

Tutoring Systems

AbstractIntelligent tutoring systems (ITS) have been shown to be highly effective at promoting learning as compared to other computer-based instructional approaches. However, many ITS rely heavily on expert design and hand-crafted rules. This makes them difficult to build and transfer across domains and limits their potential efficacy. In this paper, we investigate how feedback in a large-scale ITS can be automatically generated in a data-driven way, and more specifically how personalization of feedback can lead to improvements in student performance outcomes. First, in this paper we propose a machine learning approach to generate personalized feedback in an automated way, which takes individual needs of students into account, while alleviating the need of expert intervention and design of hand-crafted rules. We leverage state-of-the-art machine learning and natural language processing techniques to provide students with personalized feedback using hints and Wikipedia-based explanations. Second, we demonstrate that personalized feedback leads to improved success rates at solving exercises in practice: our personalized feedback model is used in , a large-scale dialogue-based ITS with around 20,000 students launched in 2019. We present the results of experiments with students and show that the automated, data-driven, personalized feedback leads to a significant overall improvement of 22.95% in student performance outcomes and substantial improvements in the subjective evaluation of the feedback.

Download Full-text

Classification of Skin Disease Using Deep Learning Neural Networks with MobileNet V2 and LSTM

Sensors ◽

10.3390/s21082852 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2852

Author(s):

Parvathaneni Naga Srinivasu ◽

Jalluri Gnana SivaSai ◽

Muhammad Fazal Ijaz ◽

Akash Kumar Bhoi ◽

Wonjoon Kim ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Convolutional Neural Network ◽

Skin Disease ◽

Network Architecture ◽

Large Scale ◽

Short Term Memory ◽

Convolutional Networks ◽

Occurrence Matrix

Deep learning models are efficient in learning the features that assist in understanding complex patterns precisely. This study proposed a computerized process of classifying skin disease through deep learning based MobileNet V2 and Long Short Term Memory (LSTM). The MobileNet V2 model proved to be efficient with a better accuracy that can work on lightweight computational devices. The proposed model is efficient in maintaining stateful information for precise predictions. A grey-level co-occurrence matrix is used for assessing the progress of diseased growth. The performance has been compared against other state-of-the-art models such as Fine-Tuned Neural Networks (FTNN), Convolutional Neural Network (CNN), Very Deep Convolutional Networks for Large-Scale Image Recognition developed by Visual Geometry Group (VGG), and convolutional neural network architecture that expanded with few changes. The HAM10000 dataset is used and the proposed method has outperformed other methods with more than 85% accuracy. Its robustness in recognizing the affected region much faster with almost 2× lesser computations than the conventional MobileNet model results in minimal computational efforts. Furthermore, a mobile application is designed for instant and proper action. It helps the patient and dermatologists identify the type of disease from the affected region’s image at the initial stage of the skin disease. These findings suggest that the proposed system can help general practitioners efficiently and effectively diagnose skin conditions, thereby reducing further complications and morbidity.

Download Full-text

Towards Neuromorphic Learning Machines Using Emerging Memory Devices with Brain-Like Energy Efficiency

Journal of Low Power Electronics and Applications ◽

10.3390/jlpea8040034 ◽

2018 ◽

Vol 8 (4) ◽

pp. 34 ◽

Cited By ~ 10

Author(s):

Vishal Saxena ◽

Xinyu Wu ◽

Ira Srivastava ◽

Kehan Zhu

Keyword(s):

Machine Learning ◽

Energy Efficiency ◽

Deep Learning ◽

Large Scale ◽

Learning Algorithms ◽

Memory Devices ◽

Cognitive Computing ◽

Mixed Signal ◽

Von Neumann ◽

Emerging Memory

The ongoing revolution in Deep Learning is redefining the nature of computing that is driven by the increasing amount of pattern classification and cognitive tasks. Specialized digital hardware for deep learning still holds its predominance due to the flexibility offered by the software implementation and maturity of algorithms. However, it is being increasingly desired that cognitive computing occurs at the edge, i.e., on hand-held devices that are energy constrained, which is energy prohibitive when employing digital von Neumann architectures. Recent explorations in digital neuromorphic hardware have shown promise, but offer low neurosynaptic density needed for scaling to applications such as intelligent cognitive assistants (ICA). Large-scale integration of nanoscale emerging memory devices with Complementary Metal Oxide Semiconductor (CMOS) mixed-signal integrated circuits can herald a new generation of Neuromorphic computers that will transcend the von Neumann bottleneck for cognitive computing tasks. Such hybrid Neuromorphic System-on-a-chip (NeuSoC) architectures promise machine learning capability at chip-scale form factor, and several orders of magnitude improvement in energy efficiency. Practical demonstration of such architectures has been limited as performance of emerging memory devices falls short of the expected behavior from the idealized memristor-based analog synapses, or weights, and novel machine learning algorithms are needed to take advantage of the device behavior. In this article, we review the challenges involved and present a pathway to realize large-scale mixed-signal NeuSoCs, from device arrays and circuits to spike-based deep learning algorithms with ‘brain-like’ energy-efficiency.

Download Full-text

SHEDR: An End-to-End Deep Neural Event Detection and Recommendation Framework for Hyperlocal News Using Social Media

INFORMS Journal on Computing ◽

10.1287/ijoc.2021.1112 ◽

2021 ◽

Author(s):

Yuheng Hu ◽

Yili Hong

Keyword(s):

Neural Network ◽

Social Media ◽

Deep Learning ◽

Event Detection ◽

Large Scale ◽

Short Term Memory ◽

State Of The Art ◽

Neural Network Models ◽

Neural Event ◽

End To End

Residents often rely on newspapers and television to gather hyperlocal news for community awareness and engagement. More recently, social media have emerged as an increasingly important source of hyperlocal news. Thus far, the literature on using social media to create desirable societal benefits, such as civic awareness and engagement, is still in its infancy. One key challenge in this research stream is to timely and accurately distill information from noisy social media data streams to community members. In this work, we develop SHEDR (social media–based hyperlocal event detection and recommendation), an end-to-end neural event detection and recommendation framework with a particular use case for Twitter to facilitate residents’ information seeking of hyperlocal events. The key model innovation in SHEDR lies in the design of the hyperlocal event detector and the event recommender. First, we harness the power of two popular deep neural network models, the convolutional neural network (CNN) and long short-term memory (LSTM), in a novel joint CNN-LSTM model to characterize spatiotemporal dependencies for capturing unusualness in a region of interest, which is classified as a hyperlocal event. Next, we develop a neural pairwise ranking algorithm for recommending detected hyperlocal events to residents based on their interests. To alleviate the sparsity issue and improve personalization, our algorithm incorporates several types of contextual information covering topic, social, and geographical proximities. We perform comprehensive evaluations based on two large-scale data sets comprising geotagged tweets covering Seattle and Chicago. We demonstrate the effectiveness of our framework in comparison with several state-of-the-art approaches. We show that our hyperlocal event detection and recommendation models consistently and significantly outperform other approaches in terms of precision, recall, and F-1 scores. Summary of Contribution: In this paper, we focus on a novel and important, yet largely underexplored application of computing—how to improve civic engagement in local neighborhoods via local news sharing and consumption based on social media feeds. To address this question, we propose two new computational and data-driven methods: (1) a deep learning–based hyperlocal event detection algorithm that scans spatially and temporally to detect hyperlocal events from geotagged Twitter feeds; and (2) A personalized deep learning–based hyperlocal event recommender system that systematically integrates several contextual cues such as topical, geographical, and social proximity to recommend the detected hyperlocal events to potential users. We conduct a series of experiments to examine our proposed models. The outcomes demonstrate that our algorithms are significantly better than the state-of-the-art models and can provide users with more relevant information about the local neighborhoods that they live in, which in turn may boost their community engagement.

Download Full-text

Facing Erosion Identification in Railway Lines Using Pixel-Wise Deep-Based Approaches

Remote Sensing ◽

10.3390/rs12040739 ◽

2020 ◽

Vol 12 (4) ◽

pp. 739

Author(s):

Keiller Nogueira ◽

Gabriel L. S. Machado ◽

Pedro H. T. Gama ◽

Caio C. V. da Silva ◽

Remis Balaniuk ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

High Impact ◽

Automatic Machine ◽

Feature Representation ◽

Data Driven ◽

Maintenance Costs ◽

Crucial Step ◽

Machine Learning Methods ◽

High Resolution Images

Soil erosion is considered one of the most expensive natural hazards with a high impact on several infrastructure assets. Among them, railway lines are one of the most likely constructions for the appearance of erosion and, consequently, one of the most troublesome due to the maintenance costs, risks of derailments, and so on. Therefore, it is fundamental to identify and monitor erosion in railway lines to prevent major consequences. Currently, erosion identification is manually performed by humans using huge image sets, a time-consuming and slow task. Hence, automatic machine learning methods appear as an appealing alternative. A crucial step for automatic erosion identification is to create a good feature representation. Towards such objective, deep learning can learn data-driven features and classifiers. In this paper, we propose a novel deep learning-based framework capable of performing erosion identification in railway lines. Six techniques were evaluated and the best one, Dynamic Dilated ConvNet, was integrated into this framework that was then encapsulated into a new ArcGIS plugin to facilitate its use by non-programmer users. To analyze such techniques, we also propose a new dataset, composed of almost 2000 high-resolution images.

Download Full-text

A Physics-Infused Deep Learning Model for the Prediction of Refractive Indices and Its Use for the Large-Scale Screening of Organic Compound Space

10.26434/chemrxiv.8796950 ◽

2019 ◽

Author(s):

Mojtaba Haghighatlari ◽

Gaurav Vishwakarma ◽

Mohammad Atif Faiz Afzal ◽

Johannes Hachmann

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Large Scale ◽

Organic Molecules ◽

Learning Model ◽

Training Data ◽

Refractive Indices ◽

Learning Models ◽

Deep Learning Model ◽

Machine Learning Models

<div><div><div>We present a multitask, physics-infused deep learning model to accurately and efficiently predict refractive indices (RIs) of organic molecules, and we apply it to a library of 1.5 million compounds. We show that it outperforms earlier machine learning models by a significant margin, and that incorporating known physics into data-derived models provides valuable guardrails. Using a transfer learning approach, we augment the model to reproduce results consistent with higher-level computational chemistry training data, but with a considerably reduced number of corresponding calculations. Prediction errors of machine learning models are typically smallest for commonly observed target property values, consistent with the distribution of the training data. However, since our goal is to identify candidates with unusually large RI values, we propose a strategy to boost the performance of our model in the remoter areas of the RI distribution: We bias the model with respect to the under-represented classes of molecules that have values in the high-RI regime. By adopting a metric popular in web search engines, we evaluate our effectiveness in ranking top candidates. We confirm that the models developed in this study can reliably predict the RIs of the top 1,000 compounds, and are thus able to capture their ranking. We believe that this is the first study to develop a data-derived model that ensures the reliability of RI predictions by model augmentation in the extrapolation region on such a large scale. These results underscore the tremendous potential of machine learning in facilitating molecular (hyper)screening approaches on a massive scale and in accelerating the discovery of new compounds and materials, such as organic molecules with high-RI for applications in opto-electronics.</div></div></div>

Download Full-text