Street scene datasets, collected from Street View or dashboard cameras, offer a promising means of detecting urban objects and incidents like street flooding. However, a major challenge in using these datasets is their lack of reliable labels: there are myriad types of incidents, many types occur rarely, and ground-truth measures of where incidents occur are lacking. Here, we propose BayFlood, a two-stage approach which circumvents this difficulty. First, we perform zero-shot classification of where incidents occur using a pretrained vision-language model (VLM). Second, we fit a spatial Bayesian model on the VLM classifications. The zero-shot approach avoids the need to annotate large training sets, and the Bayesian model provides frequent desiderata in urban settings - principled measures of uncertainty, smoothing across locations, and incorporation of external data like stormwater accumulation zones. We comprehensively validate this two-stage approach, showing that VLMs provide strong zero-shot signal for floods across multiple cities and time periods, the Bayesian model improves out-of-sample prediction relative to baseline methods, and our inferred flood risk correlates with known external predictors of risk. Having validated our approach, we show it can be used to improve urban flood detection: our analysis reveals 113,738 people who are at high risk of flooding overlooked by current methods, identifies demographic biases in existing methods, and suggests locations for new flood sensors. More broadly, our results showcase how Bayesian modeling of zero-shot LM annotations represents a promising paradigm because it avoids the need to collect large labeled datasets and leverages the power of foundation models while providing the expressiveness and uncertainty quantification of Bayesian models.

The aggravating effects of climate change and the growing population in hurricane-prone areas escalate the challenges in large-scale hurricane evacuations. While hurricane preparedness and response strategies vastly rely on the accuracy and timeliness of the predicted households' evacuation decisions, current studies featuring psychological-driven linear models leave some significant limitations in practice. Hence, the present study proposes a new methodology for predicting households' evacuation decisions constructed by easily accessible demographic and resource-related predictors compared to current models with a high reliance on psychological factors. Meanwhile, an enhanced logistic regression (ELR) model that could automatically account for nonlinearities (i.e., univariate and bivariate threshold effects) by an interpretable machine learning approach is developed to secure the accuracy of the results. Specifically, low-depth decision trees are selected for nonlinearity detection to identify the critical thresholds, build a transparent model structure, and solidify the robustness. Then, an empirical dataset collected after Hurricanes Katrina and Rita is hired to examine the practicability of the new methodology. The results indicate that the enhanced logistic regression (ELR) model has the most convincing performance in explaining the variation of the households' evacuation decision in model fit and prediction capability compared to previous linear models. It suggests that the proposed methodology could provide a new tool and framework for the emergency management authorities to improve the estimation of evacuation traffic demands in a timely and accurate manner.

Learn how to build machine learning recommender systems from one of Amazon's pioneers in the field. Updated with Tensorflow Recommenders (TFRS) and Generative Adversarial Networks for recommendations (GANs) Learn how to build machine learning recommender systems from one of Amazon's pioneers in the field. Frank Kane spent over nine years at Amazon, where he managed and led the development of many of Amazon's personalized product recommendation technologies. You've seen automated recommendations everywhere - on Netflix's home page, on YouTube, and on Amazon as these machine learning algorithms learn about your unique interests, and show the best products or content for you as an individual. These technologies have become central to the largest, most prestigious tech employers out there, and by understanding how they work, you'll become very valuable to them.

Most AI and blackbox machine learning fraud detection solutions also keep the actual fundamentals of how they fight fraud a secret and how risk …

The field of computer science is exceptionally vast and ever-expanding. It will take a lifetime to just fathom its depth, forget mastering all the diversified fields. However, it's'programming' which is ubiquitous in the various branches of computer science. Programming offers a plethora of opportunities to kick-start your professional career. Now if you dabble in the art of coding (the other term for'programming'), yet the multitude of options confuses you, pore over the following article to find your niche in computer science.

The Steam gaming platform will allow video games containing virtual reality porn and other controversial content, in an abrupt reversal of policy. Valve, which owns the popular online video game store, came under fire recently after a video game billed as a "school shooting simulation" appeared on the platform. Parents of school shooting victims objected to the Active Shooter game and an online petition received more than 200,000 signatures to have it removed. Valve eventually pulled the game but says it now wants to avoid engaging in debates of how it should police its platform. "The harsh reality of this space, that lies at the root of our dilemma, is that there is absolutely no way we can navigate it without making some of our players really mad," Valve's Erik Johnson said in a post to the Steam Store on Wednesday, 6 June.