Automated plankton recognition models face significant challenges during real-world deployment due to distribution shifts (Out-of-Distribution, OoD) between training and test data. This stems from plankton's complex morphologies, vast species diversity, and the continuous discovery of novel species, which leads to unpredictable errors during inference. Despite rapid advancements in OoD detection methods in recent years, the field of plankton recognition still lacks a systematic integration of the latest computer vision developments and a unified benchmark for large-scale evaluation. T o address this, this paper meticulously designed a series of OoD benchmarks simulating various distribution shift scenarios based on the DYB-PlanktonNet dataset [27], and systematically evaluated twenty-two OoD detection methods. Extensive experimental results demonstrate that the ViM [57] method significantly outperforms other approaches in our constructed benchmarks, particularly excelling in Far-OoD scenarios with substantial improvements in key metrics. This comprehensive evaluation not only provides a reliable reference for algorithm selection in automated plankton recognition but also lays a solid foundation for future research in plankton OoD detection. T o our knowledge, this study marks the first large-scale, systematic evaluation and analysis of Out-of-Distribution data detection methods in plankton recognition. Code is available at https://github.com/BlackJack0083/

The observation of the advancing and retreating pattern of polar sea ice cover stands as a vital indicator of global warming. This research aims to develop a robust, effective, and scalable system for classifying polar sea ice as thick/snow-covered, young/thin, or open water using Sentinel-2 (S2) images. Since the S2 satellite is actively capturing high-resolution imagery over the earth's surface, there are lots of images that need to be classified. One major obstacle is the absence of labeled S2 training data (images) to act as the ground truth. We demonstrate a scalable and accurate method for segmenting and automatically labeling S2 images using carefully determined color thresholds. We employ a parallel workflow using PySpark to scale and achieve 9-fold data loading and 16-fold map-reduce speedup on auto-labeling S2 images based on thin cloud and shadow-filtered color-based segmentation to generate label data. The auto-labeled data generated from this process are then employed to train a U-Net machine learning model, resulting in good classification accuracy. As training the U-Net classification model is computationally heavy and time-consuming, we distribute the U-Net model training to scale it over 8 GPUs using the Horovod framework over a DGX cluster with a 7.21x speedup without affecting the accuracy of the model. Using the Antarctic's Ross Sea region as an example, the U-Net model trained on auto-labeled data achieves a classification accuracy of 98.97% for auto-labeled training datasets when the thin clouds and shadows from the S2 images are filtered out.

Global warming is an urgent issue that is generating catastrophic environmental changes, such as the melting of sea ice and glaciers, particularly in the polar regions. The melting pattern and retreat of polar sea ice cover is an essential indicator of global warming. The Sentinel-2 satellite (S2) captures high-resolution optical imagery over the polar regions. This research aims at developing a robust and effective system for classifying polar sea ice as thick or snow-covered, young or thin, or open water using S2 images. A key challenge is the lack of labeled S2 training data to serve as the ground truth. We demonstrate a method with high precision to segment and automatically label the S2 images based on suitably determined color thresholds and employ these auto-labeled data to train a U-Net machine model (a fully convolutional neural network), yielding good classification accuracy. Evaluation results over S2 data from the polar summer season in the Ross Sea region of the Antarctic show that the U-Net model trained on auto-labeled data has an accuracy of 90.18% over the original S2 images, whereas the U-Net model trained on manually labeled data has an accuracy of 91.39%. Filtering out the thin clouds and shadows from the S2 images further improves U-Net's accuracy, respectively, to 98.97% for auto-labeled and 98.40% for manually labeled training datasets.

Multi-hop Question Generation is the task of generating questions which require the reader to reason over and combine information spread across multiple passages using several reasoning steps. Chain-of-thought rationale generation has been shown to improve performance on multi-step reasoning tasks and make model predictions more interpretable. However, few-shot performance gains from including rationales have been largely observed only in +100B language models, and otherwise require large scale manual rationale annotation. In this work, we introduce a new framework for applying chain-of-thought inspired structured rationale generation to multi-hop question generation under a very low supervision regime (8- to 128-shot). We propose to annotate a small number of examples following our proposed multi-step rationale schema, treating each reasoning step as a separate task to be performed by a generative language model. We show that our framework leads to improved control over the difficulty of the generated questions and better performance compared to baselines trained without rationales, both on automatic evaluation metrics and in human evaluation. Importantly, we show that this is achievable with a modest model size.