Authors: JR Lee (Water Resources Research Center @ UH Mānoa), Prithviraj Pramanik (National Institute of Technology Durgapur, India / University of New South Wales), Veda Yakkali (Rutgers University), and Anastasiia Lehova (University of Hawaiʻi at Mānoa)
Author: Yufeng Luo, MCS Research Aide, University of Wyoming, Summer 2024
Hi there! My name is Spencer Ng, and I’m a rising second-year studying Computer Science and Theater & Performance Studies at the University of Chicago.
Author: Nathan Severyns (NEIU / Crocus)
Clouds have been widely studied in a variety of fields. The shape and distribution of clouds are not only important to modeling weather, but also to understand interactions between aerosol and cloud for weather research, and to develop environment forecasting models including radiation and cloud properties. Additionally, detecting and understanding cloud cover over the sky have been studied to estimate and forecast solar irradiance and performance of renewable solar photovoltaic energy generation. For this reason, examining solar irradiance in photovoltaic power grids has been investigated in many ways. Even though the purpose of each study is diverse, it is common that they have approached to analyze the magnitude of cloud coverage. In this context, answering how much cloud covers the sky is a striking problem along with other factors such as wind direction, speed, temperature, and other meteorological factors.
Authors: Saurav Koduri (University of Illinois Urbana-Champaign) and Avasyu Chukkapalli (Virginia Tech)
Introduction
Kyle Lima
Authors: Jordan Gurneau (Northwestern University), Ella Neumann (Georgia Tech / MIT), Dave MacDonald (UC Davis), Deanna DiMonte (Northwestern University), and Morty (lead)
rideshare oppurtunity
Authors: Noah Betoshana (University of California, Davis) and Liam Fitzpatrick (Michigan State University)
Ice and snowfall are incredibly important parts of a river ecosystem. The Bad River is home to wild rice, which is very temperamental and prone to natural boom/bust years. Having a snow classifier can be used to create a larger dataset of snow that can be used for a variety of these additional tasks including assisting with predicting wild rice yields.
Hello! My name is Neelanshi Varia and I am a student at Northwestern University pursuing MS in Artificial Intelligence. During my undergraduate studies, I performed research in applications of Machine Learning in the Remote Sensing area, Conversational Artificial Intelligence and 360-degree Computer Vision. This summer at Argonne, I am working on a very interesting problem involving snowflakes! (Yes, isn’t that cool?) I am working on the classification of habits of snowflakes on images acquired real-time during snowfall and blizzards.
My name is Ori Zur and I am a rising junior at Northwestern University studying computer science and music composition. This summer at Argonne, I sought to answer the following question: how well are people following social distancing guidelines in outdoor urban environments?
Solar energy is one of the cleanest and most renewable sources of energy in today’s day and age. Through the development of this project there can be a vast economic impact in the sense that power grid operators will be able to manage power supply much more efficiently and even begin to automate processes for solar energy generation. We created a model to estimate solar irradiance in the sky based on ground images taken from Waggle/Sage nodes. We are excepting that this application will support:
NOTE: This document is based on the version 1.0.3 of the traffic counter application.
A real-time vehicle tracking application based on deep neural networks was utilized to calculate traffic state. The deep neural networks that were utilized for the estimation were introduced in the ‘Vehicle Tracking’ post. The traffic state has been calculated by ‘traffic flow = traffic speed x traffic density’ (traffic_char1996, edie1963). With the equation, we need to measure two of the parameters using instruments for each parameters to estimate the third state. However, on the other hand, the application introduced in this study based on deep neural networks can calculate traffic state independently using a video source.
Clouds have long fascinated humans because of their complex and diverse nature. To gain a deeper understanding of these atmospheric phenomena, a multidisciplinary team of computer scientists, meteorologists, and machine learning experts from Northwestern-Argonne Institute of Science and Engineering (NAISE) collaborated on the National Science Foundation (NSF)-supported Sage project. The project's goal was to develop new edge computing technologies that would allow scientists to collect and analyze large amounts of data from advanced sensors in real time.
LIDAR technology, with its ability to create detailed maps of atmospheric environments, can potentially solve the issue of blockers by providing precise information about the location and height of obstructions. It proposes many benefits that can’t be offered by a regular camera, especially the fact that it provides accurate data in all different types of weather conditions including fog, rain, and low light. This information can be used to adjust solar irradiance estimates and sky predictions, making them more accurate in any setting. Current models experience difficulties in the presense of blockers and unfamiliar sky conditions. We believe LiDAR can potentially solve this issue and allow us to deploy these nodes in urban areas.
Hi there!
by Priyanjani Chandra
Water and Our Environment
Forest fires are a major problem, and have detrimental effects on the environment. Current solutions to detecting forest fires are not efficient enough, and other machine learning models have far too long computational speeds and poor accuracies. This study is a continuation of the work done by UCSD and their SmokeyNet deep learning architecture for smoke detection[1]. We compared performance of deep learning models, in order to find the best model for this issue, and to find if a simple model can compare to a complex model. The models are: VGG16, UCSD SmokeyNet, Resnet18, Resnet34, and Resnet50.