Expansion of the Arctic melting season with an earlier melt onset date (MOD) is a well-known indicator of Arctic warming. Since 1979, the pan-Arctic MOD distributions usually have been estimated using passive satellite microwave radiometer observations. However, there is a poor agreement in MOD between previous MOD detection algorithms based on passive microwave measurements, raising doubts regarding the accuracy of their MOD products. Thus, this study developed a new MOD algorithm, namely TBmax algorithm, to improve the estimation accuracy of continuous melt onset. The TBmax algorithm utilizes the microwave radiation characteristics of sea ice, and the daily brightness temperature time series shows their maximum brightness temperature on MOD. By using Advanced Microwave Scanning Radiometer 2 brightness temperature data, the pan-Arctic MOD distributions estimated from 2013 to 2021 using the TBmax algorithm successfully reproduced a feature of sea ice melting that mainly during May or June over the Arctic, including the late melting tendency of ice at high latitudes and multiyear ice. Validation with independent dataset (ice mass balance buoy data) suggested that the TBmax MODs showed superior performance compared to other previous algorithms (biases of 0.1 days vs. -2.7 and 13.9 days). As MOD can provide information about surface emissivity and the energy budget of the sea ice, the improved MOD may contribute to a more precise analysis of Arctic environment change and enhanced estimation of sea ice parameters.

Automated diagnosis using deep neural networks in chest radiography can help radiologists detect life-threatening diseases. However, existing methods only provide predictions without accurate explanations, undermining the trustworthiness of the diagnostic methods. Here, we present XProtoNet, a globally and locally interpretable diagnosis framework for chest radiography. XProtoNet learns representative patterns of each disease from X-ray images, which are prototypes, and makes a diagnosis on a given X-ray image based on the patterns. It predicts the area where a sign of the disease is likely to appear and compares the features in the predicted area with the prototypes. It can provide a global explanation, the prototype, and a local explanation, how the prototype contributes to the prediction of a single image. Despite the constraint for interpretability, XProtoNet achieves state-of-the-art classification performance on the public NIH chest X-ray dataset.

The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for sentiment classification. This information has been used to modify parts of the model (e.g., word embeddings, attention mechanisms) such that results can be customized according to the metadata. We observe that current representation methods for categorical metadata, which are devised for human consumption, are not as effective as claimed in popular classification methods, outperformed even by simple concatenation of categorical features in the final layer of the sentence encoder. We conjecture that categorical features are harder to represent for machine use, as available context only indirectly describes the category, and even such context is often scarce (for tail category). To this end, we propose using basis vectors to effectively incorporate categorical metadata on various parts of a neural-based model. This additionally decreases the number of parameters dramatically, especially when the number of categorical features is large. Extensive experiments on various data sets with different properties are performed and show that through our method, we can represent categorical metadata more effectively to customize parts of the model, including unexplored ones, and increase the performance of the model greatly.