Accurate and timely mapping of flood extent plays a crucial role in disaster management such as damage assessment and relief activities. In recent years, high-resolution optical imagery becomes increasingly available with the wide deployment of satellites and drones. However, analyzing such imagery data to extract flood extent poses unique challenges due to noises such as obstacles (e.g., tree canopies, clouds). In this paper, we propose an elevation-guided annotation tool for flood extent mapping, which allows annotators to provide the flooded/dry labels for just a few pixels to cover a large area where the labels of most other pixels are automatically inferred. The physical rule we use here to guide the automatic label inference is that if a location is flooded (resp. dry), then its adjacent locations with a lower (resp. higher) elevation must also be flooded (resp. dry). In this way, annotators just need to label the pixels that they are confident with, and the true labels of many ambiguous pixels such as tree-canopy ones can be automatically inferred. We demonstrate the usage of our annotation tool using high-resolution aerial imagery from National Oceanic and Atmospheric Administration (NOAA) National Geodetic Survey (NGS) together with the corresponding Digital Elevation Model (DEM) data. The annotated data can be used to train machine learning models for flood extent mapping, and we train U-Net models to infer the flood map for an unseen region and achieve a high accuracy. Our annotation tool is open-sourced at https://github.com/SaugatAdhikari/Flood-Annotation-Tool.

iPSCs are pluripotent stem cells generated from adult tissue through a process called cellular reprogramming. However, cellular reprogramming is a lengthy and inefficient process since only a small fraction of cells can reliably become iPSCs. The reprogramming efficiency is generally measured by counting the number of reprogrammed colonies that emerge and grow as rounded clusters of compact cells around 20 days after adding the reprogramming vectors. However, counting colonies manually is labor-intensive, time-consuming, and error-prone.This work develops a semi-automated tool for colony counting from iPSC culture plate images, where colonies are automatically annotated with their centers. Our model uses multi-task learning to jointly predict the colony centers and conduct colony segmentation, in hope that the latter will improve the performance of the former. An annotation tool is developed to facilitate the collection of ground-truth masks by crowdsourcing. Two center-based loss functions are investigated and compared, one based on oriented Gaussian kernel and the other based on average Hausdorff distance. Extensive experiments verify that (i) the former loss outperforms the latter, (ii) the segmentation head is effective in improving center predictions. Our code has been released at https://github.com/MTSami/iPSC-Colony-Counting.

Micromobility refers to small, lightweight vehicles such as shared bicycles and electric scooters (e-scooters). Recently, shared micromobility services see increasing deployment in urban areas to solve the "last mile´ problem, where the travel distance is considered long when walking on foot, but not worth driving a car (e.g., to avoid parking). A key question to ask when deciding whether to deploy a shared micromobility service in an area is: how much car traffic can be reduced during peak hours if this service is deployed? This work answers this question by agent-based transportation simulation. The key challenge here is to generate a realistic synthetic population of the target area along with their travel day-plans. We propose to use an area-specific travel survey plus openly available data sources for this purpose, and demonstrate our approach through a case study that studied the traffic impacts of deploying dockless e-scooters in Birmingham, AL. A demo of our simulation is available at https://youtu.be/zh_mHQ6ck4U.

Micromobility refers to small, lightweight vehicles such as shared bicycles and electric scooters (e-scooters). Recently, shared micromobility services see increasing deployment in urban areas, especially for trips where the travel distance is considered long for walking, but not worth driving a car (e.g., to avoid parking). A key question to ask when deciding whether to deploy a shared micromobility service in an area is: how much car traffic can be reduced during peak hours if this service is deployed? This work answers this question by agent-based transportation simulation. The key contribution is to generate a realistic synthetic population of transportation users in the target area along with their travel day-plans, using an area-specific travel survey plus openly available data sources. We demonstrate our approach through a case study on the deployment of dockless e-scooters in Birmingham, AL, with a demo at https://youtu.be/zh_mHQ6ck4U.