IoT and Generative AI for Smart Environmental Governance

The Ministry of Economic Affairs, Department of Industrial Technology has commissioned the Industrial Technology Research Institute's Center for Smart Sensing and System Technology to develop a "Composite Long-Term Air Quality Sensor." This sensor is capable of simultaneously measuring particulate matter (PM2.5), ozone (O3), carbon monoxide (CO), volatile organic compounds (VOC), and other air quality monitoring parameters. The sensor utilizes optical detection methods to detect concentrations of suspended particulate matter (PM2.5) and ozone (O3) in the air. Innovative key technologies, including dual-channel micro-particle sieving, micro-particle signal feature recognition, LED dynamic light source stability, and multi-environmental factor compensation, are employed to enhance the sensor's lifespan and accuracy. Furthermore, semiconductor and micro-electromechanical (MEMS) technologies are utilized to create a micro-heating chip. This chip, combined with gas nano-sensing materials and a single-chip sensing control circuit, converts the detected gas sensing resistance changes into carbon monoxide concentration values for the detection of carbon monoxide (CO), total volatile organic compounds (TVOC), and other harmful and odorous gas concentrations.

The Ministry of Economic Affairs, Industrial Technology Bureau, has commissioned the Smart Sensing and System Technology Center at the Industrial Technology Research Institute (ITRI) to develop a "Composite Water Quality Sensing System." This system enables simultaneous measurement and detection of parameters such as Chemical Oxygen Demand (COD), Suspended Solid Concentration (SS), Copper Ion (Cu2+) concentration, conductivity, pH value, temperature, and more. Employing UV light sterilization, it inhibits the attachment and growth of biological films on the sensing interface, preventing interference with sensor accuracy and extending the sensor cleaning cycle. With a design incorporating water sampling, optimized power management technology, and reduced reliance on frequent manual maintenance, the system achieves long-term operational efficiency. It has been successfully applied in various settings, including industrial zones, aquaculture, chemical plating lines, metal electroplating industries, and landfill sites. The system provides intelligent wastewater discharge management and real-time monitoring of processes, meeting the demands of low-carbon management and waste reduction.

This exhibition is an atmospheric physical-chemical grid model for prediction of changes in air quality, utilizing data from the U.S. NCEP global weather forecast and regional air pollutant emissions. Local scientific investigation data has been used to adjust and calibrate the model and thereby largely improve the accuracy of the air quality forecast over Taiwan. The 3D display system enables us to understand the transmission processes of cross-border and local air pollution. The system is capable of simulating the changes in air quality over the next three days (72 hours) in Taiwan, with a temporal resolution of 1 hour and a spatial resolution of 3 km. The simulated data can be integrated with air quality data from the Civil IoT Taiwan, providing air quality forecasts every three hours (totaling 72 hours) for six metropolitan areas This system offers regulatory authorities up-to-date information on air quality trends in Taiwan, as well as critical data for formulating control strategies.

The Smart Dust Sensor technology is an innovative solution for integrating IoT networks into air quality monitoring. Developed collaboratively by the National Science and The National Science and Technology Council (NSTC), in collaboration with Taiwan Instrument Research Institute (TIRI) and Taiwan Semiconductor Research Institute (TSRI) of NARLabs, and leading academic teams in Taiwan, this technology has successfully miniaturized gas sensors while achieving low power consumption and high sensitivity. Its core features include exceptional sensitivity and stability, enabling real-time monitoring of multiple gases. Moreover, the fully domestically developed technology reduces dependence on imports and offers cost-effective sensor modules, driving the widespread adoption of air quality monitoring devices. The Smart Dust Sensor has undergone extensive field testing and third-party certifications across various applications. These include environmental monitoring stations (e.g., Taichung Dali Station), public recreational areas (e.g., odor monitoring in public restrooms), and industrial settings (e.g., semiconductor facilities and wastewater treatment plants). With its proven accuracy, reliability, and traceable data, the technology plays a key role in advancing air quality monitoring solutions, facilitating the development of smart cities, and contributing to improved environmental management.

In the past, human operation and judgment were required, but now technology assists people in handling water distribution work. Set up water level or flow sensing devices in important water supply channels and transmit the collected data to the information management platform. Using online information or mobile APPs, water stewards can instantly grasp the field water distribution to achieve the goals of saving manpower and accurately allocating water. Taking the research results of the Jianan Irrigation District as an example, water stewards management can save about 20 to 25% of water by allocating irrigation water. If it is combined with Smart irrigation system, it can save another 5% of water. Currently, Water Resources Department, MOEA continues to cooperate with National Science and Technology Council, Ministry of Agriculture to gradually expand to 3,000 hectares in the Jianan Irrigation District and 3,000 hectares in the Kaohsiung Irrigation District, and gradually promote Smart irrigation and water-saving management technology.

The Irrigation Agency has designated the Zhudong Irrigation Area in Hsinchu as a demonstration site for the construction of a smart irrigation system. This system integrates hydrological sensing components, IoT transmission, and remote gate control technology. Key control points along the irrigation channels have been equipped with water level sensors, remote gate control systems, and surveillance cameras, incorporating cost-effective, low-power, and highly weather-resistant sensing technologies. Irrigation managers can utilize water level sensors to accurately monitor changes in water levels along the irrigation channels. Coupled with real-time imaging, they can remotely control the opening and closing of water gates, optimizing water distribution management and reducing water loss during transportation. This approach not only enhances irrigation efficiency but also minimizes the time and labor costs associated with on-site operations, increasing flexibility in personnel allocation. In response to the growing frequency of extreme weather events due to climate change, the Irrigation Agency is employing smart irrigation systems to enhance the overall allocation of agricultural water resources, strengthen disaster response capabilities, and provide critical data for informed decision-making.

The application of digital twin technology in building smart cities is becoming increasingly clear, serving as a crucial engine for driving urban transformation. In the development of smart cities in recent years, citizens can view the growth and development of the entire city, including population growth, new construction, and other major activities, in a 3D format, gradually emphasizing the concept of a virtual city. Digital twin technology can simulate disaster scenarios, including weather events and traffic accidents, assisting disaster response personnel in rapidly understanding the situation and optimizing the efficiency of disaster response. In recent years, with the advancement of aerial photography, simulation technology, and computing resources, The National Science and Technology Center for Disaster Reduction has leveraged advanced technology to create a mountainous flood inundation model system. This system enhances disaster warning and impact analysis, providing a comprehensive view of vulnerable settlements. It utilizes dynamic models and virtual-real integration, presenting alert information and disaster impacts through visual elements, contributing to informed decision-making in disaster situations.

Provide EOC at all levels to disaster management, notification and response, task dispatch, evacuation and shelter, resource scheduling, search and rescue, analysis Statistics, etc. after a disaster occur. Strengthen the collaborative response and dispatch capabilities of central and local governments in large-scale disasters. Minimize the damages caused by disasters. Disaster prevention and relief data are presented in visual charts, showing the latest disaster situation in the disaster area, and can include a variety of warning messages, disaster information, monitoring information, disaster response information and other graphics layers. The graphical interface decision-making dashboard can display important commands Decision-making auxiliary information is provided to commanders at all levels for reference, and then they can issue disaster relief response instructions according to different situations, strengthen the effective use and management of resources, and increase disaster relief energy.

NCREE has developed a Hybrid earthquake early warning system (EEWS) by integrating on-site EEWS from NCREE and regional EEWS from Central Weather Administration (CWA). Within a 10 to 100-kilometer radius from the earthquake epicenter in the local region, this system can provide 3 to 15 seconds of warning time. To achieve effective alerts with the available warning time, the utilization of a Hybrid EEWS cloud platform is crucial. This platform facilitates the transmission of alerts and the affected administrative regions to various industries. Industries, in turn, leverage these alerts to develop warning systems and automated control devices tailored to meet the specific requirements of different environments. This approach aims to minimize secondary damages resulting from earthquakes, transforming EEWS beyond being notifications received Presidential Alert on mobile phones. Instead, it offers a multi-faceted alerting and disaster reduction application system tailored to different environmental settings.

Civil IoT Taiwan is part of the government’s Forward-looking Infrastructure Development Program under the Digital Construction initiative. With the collaborative efforts of the National Science Council, Ministry of Environment, Ministry of Economic Affairs, Ministry of Agriculture, Ministry of Transportation, Ministry of the Interior, Ministry of Digital Affairs, and Academia Sinica, the project is jointly executed across departments, prioritizing four key areas: air quality, water resources, earthquakes, and disaster prevention and response. By leveraging artificial intelligence and IoT technologies, various smart living services are developed to assist the government and the public in jointly addressing the challenges brought by environmental changes. By combining the innovative power of industry, academia, and research, the project aims to develop the IoT industry ecosystem and export solutions internationally.

The Central Weather Administration (CWA) is the government agency responsible for earthquake monitoring and reporting in Taiwan. In order to reduce fatalities and property losses caused by earthquakes, a high-density real-time seismic network and the advanced earthquake early warning (EEW) system have been implemented and in operation. Currently, the CWA EEW system can issue the warning message in about 10 seconds after a strong earthquake occurring in or very near Taiwan. Starting from 2021, in order to further enhance the benefit of EEW to the practical earthquake hazard mitigation, the CWA has begun to develop the customized urban EEW system. By means of introducing the on-site earthquake early warning methods, and developing the artificial intelligence models. The systems, particularly for the big urban shallow earthquake, aim to further shorten the time of EEW to 7 seconds. That means it can give warning to the areas about 25 km away from the epicenter, and more people could be alerted before the destructive shaking.

The Civil IoT data service platform collected and stored environmental sensor data in four key areas: earthquake, water resources, air quality, and disaster prevention, and provides real-time data service using the OGC SensorThings API that conforms to the international data modeling standards for value-added services through a unified data modeling framework. In order to solve the problem of insufficient communication in remote areas, Band20 frequency band is utilized to build a backbone network core service for IoT application, which provides remote areas with the use of Band20 frequency band as a network communication method for IoT data transmission, and expands the scope of IoT deployment in remote areas.