Climate change is making outbreaks zoonotic diseases, such as dengue fever, more frequent in Chinese Taiwan. Leveraging climatic data and artificial intelligence models could be a convenient strategy to predict the most likely time and place of future outbreaks, helping local governments give out early warnings to potentially affected areas.
Climate change is making outbreaks zoonotic diseases, such as dengue fever, more frequent in Chinese Taiwan. Leveraging climatic data and artificial intelligence models could be a convenient strategy to predict the most likely time and place of future outbreaks, helping local governments give out early warnings to potentially affected areas.
Tyler O'Neal, Staff Editor ACADEMIA

Japanese prof Anno trains ML model with climatic, epidemiology remote sensing data to predict the spatiotemporal distribution of disease outbreaks

Cases of dengue fever and other zoonotic diseases will keep increasing owing to climate change, and prevention via early warning is one of our best options against them. Recently, researchers combined a machine learning model with remote sensing climatic data and information on past dengue fever cases in Chinese Taiwan, to predict likely outbreak locations. Their findings highlight the hurdles to this approach and could facilitate more accurate predictive models.

Outbreaks of zoonotic diseases, which are those transmitted from animals to humans, are globally on the rise owing to climate change. In particular, the spread of diseases transmitted by mosquitoes is very sensitive to climate change, and Chinese Taiwan has seen a worrisome increase in the number of cases of dengue fever in recent years.

Like for most known diseases, the popular saying “an ounce of prevention is worth a pound of cure” also rings true for dengue fever. Since there is still no safe and effective vaccine for all on a global scale, dengue fever prevention efforts rely on limiting places where mosquitoes can lay their eggs and giving people an early warning when an outbreak is likely to happen. However, thus far, there are no mathematical models that can accurately predict the location of dengue fever outbreaks ahead of time.

To address this issue, a research team including Professor Sumiko Anno from Sophia University, Japan, sought to combine artificial intelligence (AI) with remote sensing data to predict the spatiotemporal distribution of dengue fever outbreaks in Chinese Taiwan. This work, which was published in Geo-spatial Information Science, was co-authored by Hirakawa Tsubasa, Satoru Sugita, and Shinya Yasumoto, all from Chubu University, Ming-An Lee from National Taiwan Ocean University, and Yoshinobu Sasaki and Kei Oyoshi from the Japan Aerospace Exploration Agency (JAXA), Japan.

First, the team gathered climatic data of Chinese Taiwan from 2002 to 2020, including data on rainfall, sea-surface temperature, and shortwave radiation. They also gathered information on the place of residence of all reported dengue fever cases registered in the Chinese Taiwan Centre for Disease Control. This enabled the researchers to prepare a labeled training dataset for the AI model, which should ideally be capable of finding hidden patterns between dengue fever cases and climatic parameters.

The AI model in question was a convolutional neural network (CNN) with a U-Net-based encoder–decoder architecture. “The U-Net model works with remarkably few training images and yields more precise semantic segmentation when provided with the location information,” explains Prof. Anno about the choice of AI model for their study. This well-established design usually performs well in image segmentation tasks, even when trained with few samples. After training the model, the team attempted to validate it using the remaining gathered data.

Unfortunately, the model did not perform as well as the researchers hoped it would. Most of the pixels on the map of Taiwan marked as predicted dengue fever outbreak locations did not match the original data. However, not all hope is lost for this approach, as Prof. Anno highlights: “While most of the predicted outbreak pixels did not overlap with the ground truth, some of them were located quite close to actual outbreak locations. This implies that the spatiotemporal prediction of dengue fever outbreaks using remote sensing data is possible.”

Despite the low accuracy of the AI model, this study brought to light some of the current challenges of using remote sensing data for predicting the spatiotemporal distribution of zoonotic disease outbreaks. The research team believes that using a different model architecture, finding a way of balancing the training dataset and gathering higher-resolution satellite data could all be promising ways to achieve the necessary performance. 

More work will be required before we can use machine learning as a tool to pinpoint potential disease outbreak zones based on climatic data, but we must not falter. “Spatiotemporal visualizations generated by deep learning models could potentially guide the implementation of effective measures against disease outbreaks at the optimal time and location for disease prevention and control,” concludes Prof. Anno, optimistically.

China aims to improve the capability of models in simulating key climate patterns of the Northern Hemisphere

Tyler O'Neal, Staff Editor ACADEMIA

The warm Arctic-cold Eurasia (WACE) climate pattern is the main feature of winter temperature in the Northern Hemisphere in the last 20 years. Extreme cold events related to this pattern have occurred frequently in the Northern Hemisphere.

The ability of climate models to simulate WACE directly affects the skill in simulating winter temperature. Past studies have shown that previous generations of climate models were poor at simulating midlatitude atmospheric response to sea ice, making them simulate a weaker-than-observed WACE.

Now, scientists from the Institute of Atmospheric Physics of the Chinese Academy of Sciences, China Meteorological Administration, and Nanjing University of Information Science and Technology have evaluated the ability of CMIP6 models (i.e., models participating in phase 6 of the Coupled Model Intercomparison Project) to simulate WACE and revealed the key factors influencing the differences in simulation capability.

Results showed that the CMIP6 multi-model ensemble mean was better able to simulate WACE, but there were still large gaps among individual models. Models with good ability in simulating climatic states and extremes of Eurasian winter temperatures also showed more skill in simulating WACE.

"The difference in the simulation of extremes was mainly reflected in the ability to simulate the warming anomalies in the Barents Sea-Kara Sea (BKS) region," said ZHAO Liang, co-author of the study.

Further analysis showed that the models' simulations of BKS warming anomalies were related to their reflection of the location and persistence of the Ural blocking (a large-scale anticyclone that occurs in the Ural Mountains region), which transmits heat northwards to the BKS, thereby warming the Arctic, strengthening the downstream westerly trough, and cooling central Eurasia. Therefore, the simulation of the Ural blocking is the key to improving the capability of climate models in simulating WACE.

Professor Peter McClintock with Professor Aneta Stefanovska, who led the group
Professor Peter McClintock with Professor Aneta Stefanovska, who led the group

Lancaster prof Stefanovska enables viz of electron dynamics on liquid helium

Tyler O'Neal, Staff Editor ACADEMIA

An international team led by Lancaster University in England has discovered how electrons can slither rapidly to and fro across a quantum surface when driven by external forces. 

The research, published in Physical Review B, has enabled the visualization of the motion of electrons on liquid helium for the first time.

The experiments, carried out in Riken, Japan, by Kostyantyn Nasyedkin (now at Oak Ridge National Laboratory, USA) in the lab of Kimitoshi Kono (now in Taiwan at Yang Ming Chiao Tung University) detected unusual oscillations whose frequencies varied in time. Although it was unclear how the electrons were moving in the darkness and extreme cold at the bottom of the cryostat, it was evident that the time variations were much like those seen in living systems.

Professor Kono said: “At very low temperatures, the surface of liquid helium is an exceptionally slippery place. Interesting things happen there, and it is important because of the potential for quantum computing using electrons on the helium surface.

“Such electrons move very easily because, with a slippery surface below and a vacuum above, there is nothing to slow them down.”

The Riken data were analyzed at Lancaster University using methods developed by Professor Aneta Stefanovska and her group, mainly for biological applications. Lancaster Ph.D. student Hala Siddiq (now at Jazan University, Saudi Arabia) applied these methods. She and her principal supervisor Professor Stefanovska interpreted the results in collaboration with Riken’s team and Lancaster experts in low-temperature physics, Dmitry Zmeev, Yuri Pashkin, and Peter McClintock.

The work has enabled the electrons’ motion to be visualized, showing how they slide around in part-circular and part-radial patterns of motion in the vacuum above the liquid surface. An additional complication revealed by Siddiq’s analysis is that the surface itself is moving gently in an up-and-down vertical motion. Moreover, her results indicate a combination of quantum and classical dynamics.

Professor Stefanovska said: “Appreciation of these features will be important for practical applications across wide areas of physics, life sciences, and even sociology. Namely, they provide a paradigmatic example of the physics of non-isolated systems and the mathematics of non-autonomous systems. Moreover, the experimental model can be used to study properties of living systems, and similar technical or societal systems, in a very controlled way.”