Search for: All records

Accurate streamflow prediction is critical for ensuring water supply and detecting floods, while also providing essential hydrological inputs for other scientific models in fields such as climate and agriculture.Recently, deep learning models have been shown to achieve state-of-the-art regionalization performance by building a global hydrologic model. These models predict streamflow given catchment physical characteristics and weather forcing data.However, these models are only focused on gauged basins and cannot adapt to ungaugaed basins, i.e., basins without training data. Prediction in Ungauged Basins (PUB) is considered one of the most important challenges in hydrology, as most basins in the United States and around the world have no observations. In this work, we propose a meta-transfer learning approach by enhancing imperfect physics equations that facilitate model adaptation. Intuitively, physical equations can often be used to regularize deep learning models to achieve robust regionalization performance under gauged scenarios, but they can be inaccurate due to the simplified representation of physics. We correct such uncertainty in physical equation by residual approximation and let these corrected equations guide the model training process. We evaluated the proposed method for predicting daily streamflow on the catchment attributes and meteorology for large-sample studies (CAMELS) dataset. The experiment results on hydrological data over 19 years demonstrate the effectiveness of the proposed method in ungauged scenarios.

 

Recent advancements in federated learning (FL) have greatly facilitated the development of decentralized collaborative applications, particularly in the domain of Artificial Intelligence of Things (AIoT). However, a critical aspect missing from the current research landscape is the ability to enable data-driven client models with symbolic reasoning capabilities. Specifically, the inherent heterogeneity of participating client devices poses a significant challenge, as each client exhibits unique logic reasoning properties. Failing to consider these device-specific specifications can result in critical properties being missed in the client predictions, leading to suboptimal performance. In this work, we propose a new training paradigm that leverages temporal logic reasoning to address this issue. Our approach involves enhancing the training process by incorporating mechanically generated logic expressions for each FL client. Additionally, we introduce the concept of aggregation clusters and develop a partitioning algorithm to effectively group clients based on the alignment of their temporal reasoning properties. We evaluate the proposed method on two tasks: a real-world traffic volume prediction task consisting of sensory data from fifteen states and a smart city multi-task prediction utilizing synthetic data. The evaluation results exhibit clear improvements, with performance accuracy improved by up to 54% across all sequential prediction models.

 

We are interested in understanding the complexities associated with student navigation of engineering. As part of a study associated with a larger project, we interviewed five upper division, undergraduate women of color in engineering during the Fall 2022 semester. In this paper, we present preliminary results from one participant, Nadia, and discuss the codebook development process. Insights from this paper can inform practice and research. Notably, it can help develop more responsive support structures in engineering for students from marginalized groups, specifically WOC. Furthermore, insight about codebook development can help inform qualitative research practices in engineering education. 

Internships are known to be valuable experiences for engineering students, as they provide students with hands-on engineering experience and development of professional skills. However, less is known about internships in terms of how they develop engineering students' skills related to social impact considerations. In this work in progress paper, we conducted semi structured interviews with 10 engineering students who participated in engineering internships during the previous summer. Our preliminary results indicate that while students believe that engineers should consider the social impact of their work, those same engineering students are not always equipped with the tools to discuss the social impact of their internship projects. Thus, we demonstrate a need for more intentional development of connections between engineering work and social impact during internships and in engineering curriculum.