Search for: All records

Accurate predictions of water temperature are the foundation for many decisions and regulations, with direct impacts on water quality, fishery yields, and power production. Building accurate broad-scale models for lake temperature prediction remains challenging in practice due to the variability in the data distribution across different lake systems monitored by static and time-series data. In this paper, to tackle the above challenges, we propose a novel machine learning based approach for integrating static and time-series data in deep recurrent models, which we call Invertibility-Aware-Long Short-Term Memory(IA-LSTM), and demonstrate its effectiveness in predicting lake temperature. Our proposed method integrates components of the Invertible Network and LSTM to better predict temperature profiles (forward modeling) and infer the static features (i.e., inverse modeling) that can eventually enhance the prediction when static variables are missing. We evaluate our method on predicting the temperature profile of 450 lakes in the Midwestern U.S. and report a relative improvement of 4\% to capture data heterogeneity and simultaneously outperform baseline predictions by 12\% when static features are unavailable. 

High capacity end-to-end approaches for human motion (behavior) prediction have the ability to represent subtle nuances in human behavior, but struggle with robustness to out of distribution inputs and tail events. Planning-based prediction, on the other hand, can reliably output decent-but-not-great predictions: it is much more stable in the face of distribution shift (as we verify in this work), but it has high inductive bias, missing important aspects that drive human decisions, and ignoring cognitive biases that make human behavior suboptimal. In this work, we analyze one family of approaches that strive to get the best of both worlds: use the end-to-end predictor on common cases, but do not rely on it for tail events / out-of-distribution inputs -- switch to the planning-based predictor there. We contribute an analysis of different approaches for detecting when to make this switch, using an autonomous driving domain. We find that promising approaches based on ensembling or generative modeling of the training distribution might not be reliable, but that there very simple methods which can perform surprisingly well -- including training a classifier to pick up on tell-tale issues in predicted trajectories. 

Self-healing triboelectric nanogenerators (SH-TENGs) with fast self-healing, high output performance, and wearing comfort have wide and promising applications in wearable electronic devices. This work presents a high-performance hydrogel-based SH-TENG, which consists of a high dielectric triboelectric layer (HDTL), a self-healing hydrogel electrode layer (SHEL), and a physical cross-linking layer (PCLL). Carbon nanotubes (CNTs), obtained by a chemical vapor deposition (CVD) method, were added into polydimethylsiloxane (PDMS) to produce the HDTL. Compared with pure PDMS, the short-circuit transferred charge (44 nC) and the open circuit voltage (132 V) are doubled for PDMS with 0.01 wt% CNTs. Glycerin, polydopamine particles (PDAP) and graphene were added to poly (vinyl alcohol) (PVA) to prepare the self-healing hydrogel electrode layer. SHEL can physically self-heal in ~1 min when exposed to air. The self-healing efficiency reaches up to 98%. The PCLL is made of poly(methylhydrosiloxane) (PMHS) and PDMS. It forms a good physical bond between the hydrophilic hydrogel and hydrophobic PDMS layers. The electric output performance of the SH-TENG can reach 94% of the undamaged one in 1 min. The SH-TENG (6 × 6 cm2) exhibits good stability and superior electrical performance, enabling it to power 37 LEDs simultaneously. 

This paper proposes a physics-guided machine learning approach that combines machine learning models and physics-based models to improve the prediction of water flow and temperature in river networks. We first build a recurrent graph network model to capture the interactions among multiple segments in the river network. Then we transfer knowledge from physics-based models to guide the learning of the machine learning model. We also propose a new loss function that balances the performance over different river segments. We demonstrate the effectiveness of the proposed method in predicting temperature and streamflow in a subset of the Delaware River Basin. In particular, the proposed method has brought a 33%/14% accuracy improvement over the state-of-the-art physics-based model and 24%/14% over traditional machine learning models (e.g., LSTM) in temperature/streamflow prediction using very sparse (0.1%) training data. The proposed method has also been shown to produce better performance when generalized to different seasons or river segments with different streamflow ranges.