In this study, a set of deep convolutional neural networks (CNNs) was designed for estimating the intensity of tropical cyclones (TCs) over the Northwest Pacific Ocean from the brightness temperature data observed by the Advanced Himawari Imager onboard the Himawari-8 geostationary satellite. We used 97 TC cases from 2015 to 2018 to train the CNN models. Several models with different inputs and parameters are designed. A comparative study showed that the selection of different infrared (IR) channels has a significant impact on the performance of the TC intensity estimate from the CNN models. Compared with the ground truth Best Track data of the maximum sustained wind speed, with a combination of four channels of data as input, the best multicategory CNN classification model has generated a fairly good accuracy (84.8%) and low root mean square error (RMSE, 5.24 m/s) and mean bias (−2.15 m/s) in TC intensity estimation. Adding attention layers after the input layer in the CNN helps to improve the model accuracy. The model is quite stable even with the influence of image noise. To reduce the side-effect of the very unbalanced distribution of TC category samples, we introduced a focal_loss function into the CNN model. After we transformed the multiclassification problem into a binary classification problem, the accuracy increased to 88.9%, and the RMSE and the mean bias are significantly reduced to 4.62 and −0.76 m/s, respectively. The results show that our CNN models are robust in estimating TC intensity from geostationary satellite images.

This paper developed a deep learning (DL) model for forecasting tropical cyclone (TC) intensity in the Northwest Pacific. A dataset containing 20 533 synchronized and collocated samples was assembled, which included ERA5 reanalysis data as well as satellite infrared (IR) imagery, covering the period from 1979 to 2021. The u-, v- and w-components of wind, sea surface temperature, IR satellite imagery, and historical TC information were selected as the model inputs. Then, a TC-intensity-forecast-fusion (TCIF-fusion) model was developed, in which two special branches were designed to learn multi-factor information to forecast 24 h TC intensity. Finally, heatmaps capturing the model’s insights are generated and applied to the original input data, creating an enhanced input set that results in more accurate forecasting. Employing this refined input, the heatmaps (model knowledge) were used to guide TCIF-fusion model modeling, and the model-knowledge-guided TCIF-fusion model achieved a 24 h forecast error of 3.56 m s⁻¹ for Northwest Pacific TCs spanning 2020–2021. The results show that the performance of our method is significantly better than the official subjective prediction and advanced DL methods in forecasting TC intensity by 4% to 22%. Additionally, compared to operational approaches, model-guided knowledge methods can better forecast the intensity of landfalling TCs.

Edwardsiella tarda is a Gram-negative bacterial pathogen with a broad host range that includes fish and humans. In this study, we examined the activity and function of the lysozyme inhibitor Ivy (named Ivy_Et) identified in the pathogenic E. tarda strain TX01. Ivy_Et possesses the Ivy signature motif CKPHDC in the form of ⁸²CQPHNC⁸⁷ and contains several highly conserved residues, including a tryptophan (W55). For the purpose of virulence analysis, an isogenic TX01 mutant, TXivy, was created. TXivy bears an in-frame deletion of the ivy_Et gene. A live infection study in a turbot (Scophthalmus maximus) model showed that, compared to TX01, TXivy exhibited attenuated overall virulence, reduced tissue dissemination and colonization capacity, an impaired ability to replicate in host macrophages, and decreased resistance against the bactericidal effect of host serum. To facilitate functional analysis, recombinant Ivy_Et (rIvy) and three mutant proteins, i.e., rIvyW55A, rIvyC82S, and rIvyH85D, which bear Ala, Ser, and Asp substitutions at W55, C82, and H85, respectively, were prepared. In vitro studies showed that rIvy, rIvyW55A, and rIvyH85D were able to block the lytic effect of lysozyme on a Gram-positive bacterium, whereas rIvyC82S could not do so. Likewise, rIvy, but not rIvyC82S, inhibited the serum-facilitated killing effect of lysozyme on E. tarda. In vivo analysis showed that rIvy, but not rIvyC82S, restored the lost pathogenicity of TXivy and enhanced the infectivity of TX01. Together these results indicate that Ivy_Et is a lysozyme inhibitor and a virulence factor that depends on the conserved C82 for biological activity.

Tropical cyclones (TCs), particularly those that rapidly intensify (RI), pose a significant threat due to the uncertainty in forecasting them. RI TC periods, which intensify by at least 13 m/s within 24 h, remain challenging to forecast accurately. Existing models achieve a probability of detection (POD) of 82.6% and a false alarm rate (FARate) of 27.2%. To address this, we developed a contrastive-based RI TC forecasting (RITCF-contrastive) model, utilizing satellite infrared imagery alongside atmospheric and oceanic data. The RITCF-contrastive model was tested on 1,149 TC periods in the Northwest Pacific from 2020 to 2021, achieving a POD of 92.3% and a FARate of 8.9%. RITCF-contrastive improves on previous models by addressing sample imbalance and incorporating TC structural features, leading to a 11.7% improvement in POD and a 3 times reduction in FARate compared to existing deep learning methods. The RITCF-contrastive model not only enhances RI TC forecasting but also offers a unique approach to forecasting these dangerous weather events.

Precipitation forecasting in tropical cyclones (TC) is vital for warning systems and disaster management. Artificial intelligence (AI)‐based methods show promise in this domain. Here, we investigate two aspects of AI forecasting for TC precipitation: modeling satellite image sequencing and analyzing predictability. To the former, using the Global Precipitation Measurement, we establish a high‐accuracy regional and intensity forecasting method. Through an analysis of precipitation patterns and intensities, we have demonstrated the effectiveness, reliability, and robustness of forecasting TC precipitation. To the latter, we conduct predictability research, which covers different intensity categories and landfall versus non‐landfall TC precipitation. The conclusions are: (a) TC precipitation varies regionally with predictability differences among intensity categories; (b) Forecasting landfalling TC precipitation is less challenging than non‐landfalling, considering TC intensity and paths. The proposed method also demonstrates strong forecasting capabilities in handling extreme and accumulated precipitation within 0–120 min, achieving an accuracy rate of 87%.