The environmental impacts of global warming driven by methane (CH4) emissions have catalyzed significant research initiatives in developing novel technologies that enable proactive and rapid detection of CH4. Several data-driven machine learning (ML) models were tested to determine how well they identified fugitive CH4 and its related intensity in the affected areas. Various meteorological characteristics, including wind speed, temperature, pressure, relative humidity, water vapor, and heat flux, were included in the simulation. We used the ensemble learning method to determine the best-performing weighted ensemble ML models built upon several weaker lower-layer ML models to (i) detect the presence of CH4 as a classification problem and (ii) predict the intensity of CH4 as a regression problem.

The number of collisions between aircraft and birds in the airspace has been increasing at an alarming rate over the past decade due to increasing bird population, air traffic and usage of quieter aircraft. Bird strikes with aircraft are anticipated to increase dramatically when emerging Advanced Air Mobility aircraft start operating in the low altitude airspace where probability of bird strikes is the highest. Not only do such bird strikes can result in human and bird fatalities, but they also cost the aviation industry millions of dollars in damages to aircraft annually. To better understand the causes and effects of bird strikes, research to date has mainly focused on analyzing factors which increase the probability of bird strikes, identifying high risk birds in different locations, predicting the future number of bird strike incidents, and estimating cost of bird strike damages. However, research on bird movement prediction for use in flight planning algorithms to minimize the probability of bird strikes is very limited. To address this gap in research, we implement four different types of Long Short-Term Memory (LSTM) models to predict bird movement latitudes and longitudes. A publicly available data set on the movement of pigeons is utilized to train the models and evaluate their performances. Using the bird flight track predictions, aircraft departures from Cleveland Hopkins airport are simulated to be delayed by varying amounts to avoid potential bird strikes with aircraft during takeoff. Results demonstrate that the LSTM models can predict bird movement with high accuracy, achieving a Mean Absolute Error of less than 100 meters, outperforming linear and nonlinear regression models. Our findings indicate that incorporating bird movement prediction into flight planning can be highly beneficial.

AI has been proposed as an important tool to support several efforts related to nature-based climate solutions such as the detection of wildfires that affect forests and vegetation-based offsets. While this and other use-cases provide important demonstrative value of the power of AI in climate change mitigation, such efforts have typically been undertaken in silos, without awareness of the integrative nature of real-world climate policy-making. In this paper, we propose a novel overarching framework for AI-aided integrated and comprehensive decision support for various aspects of nature-based climate decision-making. Focusing on vegetation-based solutions such as forests, we demonstrate how different AI-aided decision support models such as AI-aided wildfire detection, AI-aided vegetation carbon stock assessment, reversal risk mitigation, and disaster response planning can be integrated into a comprehensive framework. Rather than being disparate elements, we posit that the exchange of data and analytical results across elements of the framework, and careful mitigation of uncertainty propagation will provide tremendous value relative to the status-quo for real-world climate policy-making.

Pre-training large models on vast amounts of web data has proven to be an effective approach for obtaining powerful, general models in several domains, including language and vision. However, this paradigm has not yet taken hold in deep reinforcement learning (RL). This gap is due to the fact that the most abundant form of embodied behavioral data on the web consists of videos, which do not include the action labels required by existing methods for training policies from offline data. We introduce Latent Action Policies from Observation (LAPO), a method to infer latent actions and, consequently, latent-action policies purely from action-free demonstrations. Our experiments on challenging procedurally-generated environments show that LAPO can act as an effective pre-training method to obtain RL policies that can then be rapidly fine-tuned to expert-level performance. Our approach serves as a key stepping stone to enabling the pre-training of powerful, generalist RL models on the vast amounts of action-free demonstrations readily available on the web.

The growing popularity of neural machine translation (NMT) and LLMs represented by ChatGPT underscores the need for a deeper understanding of their distinct characteristics and relationships. Such understanding is crucial for language professionals and researchers to make informed decisions and tactful use of these cutting-edge translation technology, but remains underexplored. This study aims to fill this gap by investigating three key questions: (1) the distinguishability of ChatGPT-generated translations from NMT and human translation (HT), (2) the linguistic characteristics of each translation type, and (3) the degree of resemblance between ChatGPT-produced translations and HT or NMT. To achieve these objectives, we employ statistical testing, machine learning algorithms, and multidimensional analysis (MDA) to analyze Spokesperson's Remarks and their translations. After extracting a wide range of linguistic features, supervised classifiers demonstrate high accuracy in distinguishing the three translation types, whereas unsupervised clustering techniques do not yield satisfactory results. Another major finding is that ChatGPT-produced translations exhibit greater similarity with NMT than HT in most MDA dimensions, which is further corroborated by distance computing and visualization. These novel insights shed light on the interrelationships among the three translation types and have implications for the future advancements of NMT and generative AI.

Non-contrastive self-supervised learning (NC-SSL) methods like BarlowTwins and VICReg have shown great promise for label-free representation learning in computer vision. Despite the apparent simplicity of these techniques, researchers must rely on several empirical heuristics to achieve competitive performance, most notably using high-dimensional projector heads and two augmentations of the same image. In this work, we provide theoretical insights on the implicit bias of the BarlowTwins and VICReg loss that can explain these heuristics and guide the development of more principled recommendations. Our first insight is that the orthogonality of the features is more critical than projector dimensionality for learning good representations. Based on this, we empirically demonstrate that low-dimensional projector heads are sufficient with appropriate regularization, contrary to the existing heuristic. Our second theoretical insight suggests that using multiple data augmentations better represents the desiderata of the SSL objective. Based on this, we demonstrate that leveraging more augmentations per sample improves representation quality and trainability. In particular, it improves optimization convergence, leading to better features emerging earlier in the training. Remarkably, we demonstrate that we can reduce the pretraining dataset size by up to 4x while maintaining accuracy and improving convergence simply by using more data augmentations. Combining these insights, we present practical pretraining recommendations that improve wall-clock time by 2x and improve performance on CIFAR-10/STL-10 datasets using a ResNet-50 backbone. Thus, this work provides a theoretical insight into NC-SSL and produces practical recommendations for enhancing its sample and compute efficiency.

A significant challenge in applying planning technology to real-world problems lies in obtaining a planning model that accurately represents the problem's dynamics. Numeric Safe Action Models Learning (N-SAM) is a recently proposed algorithm that addresses this challenge. It is an algorithm designed to learn the preconditions and effects of actions from observations in domains that may involve both discrete and continuous state variables. N-SAM has several attractive properties. It runs in polynomial time and is guaranteed to output an action model that is safe, in the sense that plans generated by it are applicable and will achieve their intended goals. To preserve this safety guarantee, N-SAM must observe a substantial number of examples for each action before it is included in the learned action model. We address this limitation of N-SAM and propose N-SAM*, an enhanced version of N-SAM that always returns an action model where every observed action is applicable at least in some state, even if it was only observed once. N-SAM* does so without compromising the safety of the returned action model. We prove that N-SAM* is optimal in terms of sample complexity compared to any other algorithm that guarantees safety. An empirical study on a set of benchmark domains shows that the action models returned by N-SAM* enable solving significantly more problems compared to the action models returned by N-SAM.

Intent classification is a fundamental task in natural language understanding, aiming to categorize user queries or sentences into predefined classes to understand user intent. The most challenging aspect of this particular task lies in effectively incorporating all possible classes of intent into a dataset while ensuring adequate linguistic variation. Plenty of research has been conducted in the related domains in rich-resource languages like English. In this study, we introduce BNIntent30, a comprehensive Bengali intent classification dataset containing 30 intent classes. The dataset is excerpted and translated from the CLINIC150 dataset containing a diverse range of user intents categorized over 150 classes. Furthermore, we propose a novel approach for Bengali intent classification using Generative Adversarial BERT to evaluate the proposed dataset, which we call GAN-BnBERT. Our approach leverages the power of BERT-based contextual embeddings to capture salient linguistic features and contextual information from the text data, while the generative adversarial network (GAN) component complements the model's ability to learn diverse representations of existing intent classes through generative modeling. Our experimental results demonstrate that the GAN-BnBERT model achieves superior performance on the newly introduced BNIntent30 dataset, surpassing the existing Bi-LSTM and the stand-alone BERT-based classification model.

A comprehensive evaluation is critical to assess the capabilities of large multimodal models (LMM). In this study, we evaluate the state-of-the-art LMMs, namely GPT-4V and Gemini, utilizing the VQAonline dataset. VQAonline is an end-to-end authentic VQA dataset sourced from a diverse range of everyday users. Compared previous benchmarks, VQAonline well aligns with real-world tasks. It enables us to effectively evaluate the generality of an LMM, and facilitates a direct comparison with human performance. To comprehensively evaluate GPT-4V and Gemini, we generate seven types of metadata for around 2,000 visual questions, such as image type and the required image processing capabilities. Leveraging this array of metadata, we analyze the zero-shot performance of GPT-4V and Gemini, and identify the most challenging questions for both models.

Generating unit tests is a crucial task in software development, demanding substantial time and effort from programmers. The advent of Large Language Models (LLMs) introduces a novel avenue for unit test script generation. This research aims to experimentally investigate the effectiveness of LLMs, specifically exemplified by ChatGPT, for generating unit test scripts for Python programs, and how the generated test cases compare with those generated by an existing unit test generator (Pynguin). For experiments, we consider three types of code units: 1) Procedural scripts, 2) Function-based modular code, and 3) Class-based code. The generated test cases are evaluated based on criteria such as coverage, correctness, and readability. Our results show that ChatGPT's performance is comparable with Pynguin in terms of coverage. At the same time, ChatGPT's ability to generate tests is superior to Pynguin, as the latter is not able to generate test cases for Category 1. We also find that about 39% and 28% of assertions generated by ChatGPT for Category 2 and 3, respectively, were incorrect. Our results also show that there is minimal overlap in missed statements between ChatGPT and Pynguin, thus, suggesting that a combination of both tools may enhance unit test generation performance. Finally, prompt engineering improved ChatGPT's performance, achieving an average 28% coverage improvement in Category 2 and 15% improvement in Category 3 after about 4 iterations.