Tool For Warning Research Articles

Population genetic characterization of (Aedes albopictus) mosquitoes (Diptera: Culicidae) from the Yangtze River Basin of China based on rDNA-ITS2.

Aedes albopictus is an important vector of many mosquito-borne viral diseases, including dengue fever and Zika. In recent years, it has spread and colonized tropical, subtropical and temperate regions worldwide. Monitoring of Ae. albopictus population dynamics is an important tool for early warning of mosquito-borne infections. Because the genetic diversity and genetic structure of natural populations are the genetic bases of population dynamics, studies of population genetics can reveal the origin, differentiation and dispersal characteristics of Ae. albopictus populations. Then, their evolutionary potential and environmental adaptability can be analyzed, providing a theoretical basis for the formulation of accurate Ae. albopictus surveillance and integrated control programs. In 2018, 552 Ae. albopictus larvae were collected during an invasive mosquito species surveillance project in China's Yangtze River Basin. Morphological analysis was performed to assign the adult mosquitoes to species, and then the genetic marker ITS2 was amplified and sequenced. There were 179 haplotypes among 552 ITS2 sequences. In total, 155/179 (86.59%) haplotypes were specific to individual populations, and 24/179 (13.41%) haplotypes were shared by populations. Hap4 (126), Hap7 (43), and Hap16 (34) were the most numerous haplotypes and the most widely distributed. The overall Hd was 0.928, π was 0.031, the mean nucleotide difference number (K) was 7.255, and the number of segregating sites was 169. TCS network maps mainly showed a single star-like scattered distribution. According to geographical location, there were no obvious haplotype groups, and the haplotypes were intricately connected. The genetic diversity of Ae. albopictus populations in the Yangtze River Basin was high. The molecular variance observed in the populations of Ae. albopictus mainly occurred among individuals within populations, accounting for 98.79% of the total, while that among populations accounted for only 1.21% of the total. Only the populations of Ae. albopictus in the Chongqing and Sichuan regions showed a moderate degree of population genetic differentiation, while genetic differentiation between the other regions were small, gene exchange was very common, and genetic differentiation within populations was minimal. According to this study, the genetic diversity of Ae. albopictus populations in the Yangtze River Basin is high, the genetic differentiation among populations is small, and gene exchange is common. In addition, frequent interregional exchange exacerbates the abnormal spread of vectors. This study highlighted the potential spread route of the vector Ae. albopictus in the Yangtze River Basin. There are three potential dispersal routes for Ae. albopictus populations in the Yangtze River Basin. The findings could be helpful for effective surveillance and early warning of Ae. albopictus vectors.

Single-molecule lipopolysaccharides identification and the interplay with biomolecules via nanopore readout

Lipopolysaccharides (LPS) are the major constituent on the cell envelope of all gram-negative bacteria. They are ubiquitous in air, and are toxic inflammatory stimulators for urinary disorders and sepsis. The reported optical, thermal, and electrochemical sensors via the intermolecular interplay of LPS with proteins and aptamers are generally complicated methods. We demonstrate the single-molecule nanopore approach for LPS identification in distinct bacteria as well as the serotypes discrimination. With a 4 nm nanopore, we achieve a detection limit of 10 ng/mL. Both the antibiotic polymyxin B (PMB) and DNA aptamer display specific binding to LPS. The identification of LPS in both human serum and tap water show good performance with nanopore platforms. Our work shows a highly-sensitive and easy-to-handle scheme for clinical and environmental biomarkers determination and provides a promising screening tool for early warning of contamination in water and medical supplies.

Crowdsourcing data interpretation for the response to the first public tsunami alert in the Mediterranean sea, after the October 30th, 2020 earthquake (Mw7.0), Samos, Greece

On October 30, 2020, 11:51 UTC, a large shallow earthquake of moment magnitude Mw7.0 ruptured the eastern Aegean Sea area and affected several Greek islands, mainly Samos, as well as the Izmir area, western Turkey. A moderate damaging tsunami followed the earthquake and inundated many coastal zones in the area. At 12:15 UTC, the Greek Civil Protection sent to the residents of the eastern Aegean Sea Greek islands a tsunami alert via SMS through the single European emergency phone number 112. It has been the first time that a tsunami warning was publicly issued in the frame of the North-East Atlantic and Mediterranean Tsunami Warning System (NEAMTWS/IOC/UNESCO) since the system became operational during the summer of 2012. Through an on-line questionnaire survey conducted soon after the event we investigated the impact the tsunami 112 alert message had among the population. The aim of this study is to assess the effectiveness of the 112 number as a tool for tsunami early warning, to look after possible weaknesses that may need future improvements and to better understand the level of tsunami risk awareness among the population. The response received from 344 citizens clearly indicates that the particular tsunami alert in general had positive impact to the message recipients, but highlights several weaknesses of the tsunami emergency management chain in Greece and demonstrates some aspects of the 112 system that need improvement.

Dynamics of pollen beetle (Brassicogethes aeneus) immigration and colonization of oilseed rape (Brassica napus) in Europe.

Understanding the dynamics of pest immigration into an agroecosystem enables effective and timely management strategies. The pollen beetle (Brassicogethes aeneus) is a primary pest of the inflorescence stages of oilseed rape (Brassica napus). This study investigated the spatial and temporal dynamics of pollen beetle immigration into oilseed rape fields in Denmark and the UK using multiple methods, including optical sensors. In all fields, pollen beetles were found to be aggregated and beetle density was related to plant growth stage, with more beetles occurring on plants after the budding stage than before inflorescence development. Optical sensors were the most efficient monitoring method, recording pollen beetles 2 and 4 days ahead of water traps and counts from plant scouting, respectively. Optical sensors are a promising tool for early warning of insect pest immigration. The aggregation pattern of pollen beetles post immigration could be used to precisely target control in oilseed rape crops. © 2023 The Authors. Pest Management Science published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Regional aerosol forecasts based on deep learning and numerical weather prediction

Atmospheric chemistry transport models have been extensively applied in aerosol forecasts over recent decades, whereas they are facing challenges from uncertainties in emission rates, meteorological data, and over-simplified chemical parameterizations. Here, we developed a spatial-temporal deep learning framework, named PPN (Pollution-Predicting Net for PM2.5), to accurately and efficiently predict regional PM2.5 concentrations. It has an encoder-decoder architecture and combines the preceding PM2.5 observations and numerical weather prediction. Besides, the model proposes a weighted loss function to promote the forecasting performance in extreme events. We applied the proposed model to forecast 3-day PM2.5 concentrations over the Beijing-Tianjin-Hebei region in China on a three-hour-by-three-hour basis. Overall, the model showed good performance with R2 and RMSE values of 0.7 and 17.7 μg m−3, respectively. It could capture the high PM2.5 concentration in the south and relatively low concentration in the north and exhibit better performance within the next 24 h. The use of the weighted loss function decreased the level of “high values underestimation, low values overestimation”, while incorporating the preceding PM2.5 observations into the encoder phase improved the predictive accuracy within 24 h. We also compared the model result with that from a state-of-the-art numerical model (WRF-Chem with pollutant data assimilation). The temporal R2 and RMSE from the WRF-Chem were 0.30−0.77 and 19−45 μg m−3 while those from the PPN model were 0.42−0.84 and 15−42 μg m−3. The proposed model shows powerful capacity in aerosol forecasts and provides an efficient and accurate tool for early warning and management of regional pollution events.

Applying Reconstructed Daily Water Storage and Modified Wetness Index to Flood Monitoring: A Case Study in the Yangtze River Basin

The terrestrial water storage anomaly (TWSA) observed by the Gravity Recovery and Climate Experiment (GRACE) satellite and its successor GRACE Follow-On (GRACE-FO) provides a new means for monitoring floods. However, due to the coarse temporal resolution of GRACE/GRACE-FO, the understanding of flood occurrence mechanisms and the monitoring of short-term floods are limited. This study utilizes a statistical model to reconstruct daily TWS by combining monthly GRACE observations with daily temperature and precipitation data. The reconstructed daily TWSA is utilized to monitor the catastrophic flood event that occurred in the middle and lower reaches of the Yangtze River basin in 2020. Furthermore, the study compares the reconstructed daily TWSA with the vertical displacements of eight Global Navigation Satellite System (GNSS) stations at grid scale. A modified wetness index (MWI) and a normalized daily flood potential index (NDFPI) are introduced and compared with in situ daily streamflow to assess their potential for flood monitoring and early warning. The results show that terrestrial water storage (TWS) in the study area increases from early June, reaching a peak on 19 July, and then receding till September. The reconstructed TWSA better captures the changes in water storage on a daily scale compared to monthly GRACE data. The MWI and NDFPI based on the reconstructed daily TWSA both exceed the 90th percentile 7 days earlier than the in situ streamflow, demonstrating their potential for daily flood monitoring. Collectively, these findings suggest that the reconstructed TWSA can serve as an effective tool for flood monitoring and early warning.

Temperature Forecasting as a Means of Mitigating Climate Change and Its Effects: A Case Study of Mali

Temperature forecasts and trend analyzes were carried out for several locations in Mali as an important tool for warning of potentially threatening weather events such as severe heat waves, storms, droughts and floods, which could pose a great risk to humans and their environment. Five locations (Segou, Sikasso, Kayes, Gao and Taoudenni) across Mali (170 00’N – 40 00’W) were chosen for this research work. Satellite data of annual temperature obtained from the European Centre for Medium-Range Weather Forecast (ECMWF) database for 35 years (1985-2019) was used for this work. The Mann-Kendall trend test was carried out for various locations to observe and study the trend. Four Models including Auto Regressive and Integrated Moving Average (ARIMA), Exponential smoothening (ETS), TBATS (Trigonometric seasonality, Box-Cox transformation, ARMA errors, Trend and Seasonal components) and the linear model were employed to forecast average temperature for 10 years for all the locations. The model that produces the best forecast at the 95% confidence level is expected to have the lowest Root Mean Square Error (RMSE) value. The results showed that no significant trends were recorded at the considered locations. The linear model produced the best forecast for Segou, Kayes and Taoudenni, while the TBATS model produced the best forecast for Gao and the ARIMA model produced the best forecast for Sikasso.

Data-driven landslide forecasting: Methods, data completeness, and real-time warning

Various data-driven methods, including empirical, statistical, and machine learning methods, have been developed to promptly forecast rain-induced landslides. Their abilities differ considerably in spatio-temporal landslide prediction and in handling datasets of varying qualities. A challenging issue that significantly hinders the applications of data-driven methods is the data incompleteness in most landslide inventories, particularly the lack of accurate landslide time that is a vital link between each landslide and its triggering rainstorm. This study systematically compares the performances of three categories of data-driven methods for landslide prediction and proposes a novel machine learning model featured by probabilistic landslide modelling for spatio-temporal landslide prediction. The integrated machine learning model can be developed on a realistic landslide database, regardless of whether the landslide timing information is known or not. It not only promptly predicts the spatio-temporal evolution of landslides during a rainstorm but also reliably characterises the factual landslide risk, which provides a powerful real-time decision-making tool for landslide early warning and risk management. The model is validated against the landslide incidents in Hong Kong in the past 35 years both spatially and temporally, and outperforms other data-driven models in both prediction ability and accuracy.

Robust Velocity Dealiasing for Weather Radar Based on Convolutional Neural Networks

Doppler weather radar is an essential tool for monitoring and warning of hazardous weather phenomena. A large aliasing range (ra) is important for surveillance but a high aliasing velocity (va) is also important to obtain storm dynamics unambiguously. However, the ra and va are inversely related to pulse repetition time. This “Doppler dilemma” is more challenging at shorter wavelengths. The proposed algorithm employs a CNN (convolutional neural network), which is widely used in image classification, to tackle the velocity dealiasing issue. Velocity aliasing can be converted to a classification problem. The velocity field and aliased count can be regarded as the input image and the label, respectively. Through a fit-and-adjust process, the best weights and the biases of the model are determined to minimize a cost function. The proposed method is compared against the traditional region-based method. Both methods show similar performance on mostly filled precipitation. For sparsely filled precipitation; however, the CNN demonstrated better performance since the CNN processes the entire scan at once while the region-based method processes only the limited adjacent area.

Earthquake Disaster Preparedness Among Teachers in The Special School

The level of teachers' disaster preparedness in schools is one thing that influences the impact of disasters on children with disabilities, especially earthquakes, which can occur at any time, including during school hours. Therefore, this study aims to determine the description of earthquake disaster preparedness for special school teachers. This study used a quantitative descriptive method with a total sample of 37 teachers at Cileunyi State SLB, and the total sampling technique used was this study. Preparedness measurement for SLB teachers uses instruments modified according to research needs. Data analysis with frequency distribution and results were grouped into ready and unprepared categories. The results showed that 86.5% of teachers were categorized as 'ready'. The best preparedness parameter is disaster knowledge, while the lowest is disaster warning. From the study results, it can be concluded that most SLB teachers are categorized as ready to face earthquake disasters. However, it is expected that efforts to improve aspects of disaster warning can be carried out, such as providing disaster warning tools, especially for children with disabilities.

Dynamic Multi-Graph Convolution based Channel-Weighted Transformer Feature Fusion Network for Epileptic Seizure Prediction.

Electroencephalogram (EEG) based seizure prediction plays an important role in the closed-loop neuromodulation system. However, most existing seizure prediction methods based on graph convolution network only focused on constructing the static graph, ignoring multi-domain dynamic changes in deep graph structure. Moreover, the existing feature fusion strategies generally concatenated coarse-grained epileptic EEG features directly, leading to the suboptimal seizure prediction performance. To address these issues, we propose a novel multi-branch dynamic multi-graph convolution based channel-weighted transformer feature fusion network (MB-dMGC-CWTFFNet) for the patient-specific seizure prediction with the superior performance. Specifically, a multi-branch (MB) feature extractor is first applied to capture the temporal, spatial and spectral representations fromthe epileptic EEG jointly. Then, we design a point-wise dynamic multi-graph convolution network (dMGCN) to dynamically learn deep graph structures, which can effectively extract high-level features from the multi-domain graph. Finally, by integrating the local and global channel-weighted strategies with the multi-head self-attention mechanism, a channel-weighted transformer feature fusion network (CWTFFNet) is adopted to efficiently fuse the multi-domain graph features. The proposed MB-dMGC-CWTFFNet is evaluated on the public CHB-MIT EEG and a private intracranial sEEG datasets, and the experimental results demonstrate that our proposed method achieves outstanding prediction performance compared with the state-of-the-art methods, indicating an effective tool for patient-specific seizure warning. Our code will be available at: https://github.com/Rockingsnow/MB-dMGC-CWTFFNet.

Smoke target detection based on dynamic multi-frame decimation with cavity convolution

Compared with traditional smoke alarms, smoke detection based on video images has the advantages of low cost, fast response time, wide applicability, etc. Smoke detection algorithms are becoming an effective and widely used tool for early warning of fires by recognizing smoke graphic features. In this paper, we use the VGG-16 neural network as the benchmark network and improve it by using null convolution and combining it with the dynamic multi-frame subtraction method for smoke detection. The experimental results show that the proposed method is useful for early warning of smoke in the early stage of a fire before it becomes intense.

Response of ecosystem gross primary productivity to drought in northern China based on multi-source remote sensing data

Drought has become one of the main reasons for the loss of terrestrial ecosystems gross primary productivity (GPP) because of its more frequent occurrence under the background of global warming. Aiming to explore the response mechanism of vegetation under drought conditions, the sun-induced chlorophyll fluorescence (SIF), normalized difference vegetation index (NDVI) and enhanced vegetation index (EVI) were used to monitor vegetation drought and quantify the drought-induced GPP variabilities. MODIS GPP were used for analysis, which was verified by close-path eddy covariance flux (R2 = 0.69, p < 0.01). According to the standard precipitation evapotranspiration index (SPEI) and soil moisture (SM), the drought periods of 2010 and 2014 in the eastern piedmont of Taihang Mountains were selected to analyze drought impacts on GPP. We found that SIF had the ability to reflect the effects of drought prolonged action on vegetation and respond to GPP persistent changes during drought. SIF successfully described GPP loss during droughts in 2010 (20.91 gCm−2month−1) and 2014 (9.52 gCm−2month−1). SIF was more significantly linearly correlated with GPP (R2 = 0.89) than NDVI (R2 = 0.69) and EVI (R2 = 0.84), suggesting that SIF was more sensitive to physiological changes in vegetation. SIF correlated significantly higher to SM than SPEI, and there was a two-month lag to SM, which may be related to the adaptation mechanism of vegetation physiological recovery under drought conditions. Results showed that SIF is more accurate and sensitive than NDVI and EVI in regional vegetation drought monitoring and drought-induced GPP variations. SIF is an effective physiological index for timely detection and regional drought, and an effective tool for ecosystem management and disaster warning.

Genetic Programming-Based Prediction Model for Microseismic Data

Microseismic monitoring is a rock breakdown monitoring technology, and it has become a major technical tool for underground disaster warning and prevention. However, the massive amount of data involved in multipoint monitoring raises the difficulty for microseismic research when the research object involves underground large-scale complex engineering on time and space scales. The risk predictions of rockburst based on microseismic parameters rely only on the experience of researchers and subjective factors by the human factor. The dependent variable cannot be related to the acoustic and energy signals in the form of a functional equation. Therefore, we collected a large amount of microseismic data obtained from the working faces of Shoushan Mine of Pingdingshan Coal Group in China and filtered the data, then we constructed a prediction model of microseismic data based on underground spatial three-dimensional coordinates using genetic programming (GP), which can realize real-time monitoring and disaster warning of microseismic signals. We established the magnitude and energy prediction formulas by GP and obtained the real-time evolution of each parameter of the optimal individual. The results showed that the actual seismic and energy data of the working faces exhibited good agreement with those predicted by the prediction formulas. The high energy and seismic distribution were caused by the mining stress at the edge of working faces due to the excavation and unloading effect of the surface, and the energy and seismic evolution predicted by GP could also show this phenomenon well.

Urban Flood Risk Assessment in Zhengzhou, China, Based on a D-Number-Improved Analytic Hierarchy Process and a Self-Organizing Map Algorithm

Flood risk assessment is an important tool for disaster warning and prevention. In this study, an integrated approach based on a D-number-improved analytic hierarchy process (D-AHP) and a self-organizing map (SOM) clustering algorithm are proposed for urban flooding risk assessment. The urban flood inundation model and geographic information system (GIS) technology were used to quantify the assessment indices of urban flood risk. The D-AHP approach was adopted to determine the weights of the indices, which effectively makes up for the shortcomings of the AHP in dealing with uncertain evaluation information (such as fuzzy and incomplete information). In addition, the SOM clustering algorithm was applied to determine the flood risk level. It is a data-driven approach that avoids the subjective determination of a flood risk classification threshold. The proposed approach for flood risk assessment was implemented in Zhengzhou, China. The flood risk was classified into five levels: highest risk, higher risk, medium risk, lower risk, and the lowest risk. The proportion of the highest risk areas was 9.86%; such areas were mainly distributed in the central and eastern parts of the Jinshui District, the eastern part of the Huiji District, and the northeastern part of the Guancheng District, where there were low terrain and serious waterlogging. The higher risk areas accounted for 24.26% of the study area, and were mainly distributed in the western and southern parts of the Jinshui District, the southern part of the Huiji District, the middle and eastern parts of the Zhongyuan District, the northeastern part of the Erqi District, and the northwestern part of the Guancheng District, which consisted of economically developed areas of dense population and buildings, matching well with historical flooding events. To verify the effectiveness of the proposed approach, traditional approaches for risk assessment were compared. The comparison indicated that the proposed approach is more reasonable and accurate than the traditional approaches. This study showed the potential of a novel approach to flood risk assessment. The results can provide a reference for urban flood management and disaster reduction in the study area.

Early Warning Tools For Insolvency Prevention: Implementation in the Romanian Legal Framework

Early Warning Tools For Insolvency Prevention: Implementation in the Romanian Legal Framework

Optimal allocation and operation of sewer monitoring sites for wastewater-based disease surveillance: A methodological proposal

Wastewater-based epidemiology (WBE) is drawing increasing attention as a promising tool for an early warning of emerging infectious diseases such as COVID-19. This study demonstrated the utility of a spatial bisection method (SBM) and a global optimization algorithm (i.e., genetic algorithm, GA), to support better designing and operating a WBE program for disease surveillance and source identification. The performances of SBM and GA were compared in determining the optimal locations of sewer monitoring manholes to minimize the difference among the effective spatial monitoring scales of the selected manholes. While GA was more flexible in determining the spatial resolution of the monitoring areas, SBM allows stepwise selection of optimal sampling manholes with equiareal subcatchments and lowers computational cost. Upon detecting disease outbreaks at a regular sewer monitoring site, additional manholes within the catchment can be selected and monitored to identify source areas with a required spatial resolution. SBM offered an efficient method for rapidly searching for the optimal locations of additional sampling manholes to identify the source areas. This study provides strategic and technical elements of WBE including sampling site selection with required spatial resolution and a source identification method.

Seasonal trends of mercury bioaccumulation and assessment of toxic effects in Asian clams and microbial community from field study of estuarine sediment

This study investigated seasonal trends in bioaccumulation potential and toxic effects of mercury (Hg) in Asian clams (Corbicula fluminea) and microbial community. For this, a clam-exposure experiment was performed during summer, fall, and winter seasons in four different sites (HS1: control/clean site; HS2, HS3, and HS4: contaminated sites) of Hyeongsan River estuary, South Korea. Total mercury (THg) and methylmercury (MeHg) in whole sediments were highest at HS4 site during fall, sustained similar levels during winter, but decreased during summer. Unlike whole sediment, pore water reported higher levels in summer, and gradually declined during fall and winter. Asian clams from HS4 site collected during summer presented highest bioaccumulations of THg (521.52 μg/kg, dry weight) and MeHg (161.04 μg/kg, dry weight), which also correlated with the higher levels of Hg present in pore water in the same season. Moreover, biota-sediment-pore water accumulation factor (BSpAF) were comparatively greater in clams collected from HS2∼HS4 compared to HS1 sites, suggesting that porewater was a better indicator of accumulation of Hg. Upregulation of biomarker genes responsible for detoxifying process (gsts1), scavenging oxidative stress (cat), and protein reparation (hsp70 and hsp90) were observed in clams collected from HS2∼HS4. The overexpression of these biomarkers implied that Asian clams can be considered as promising warning tools for Hg-contamination. Both bacterial and metabolic diversities were negatively affected by higher levels of THg and MeHg. Phylum Proteobacteria was enriched in HS2∼HS4 compared to HS1. In contrast, phylum Bacteroidetes showed a reverse trend. The metabolic profile was highest in HS1 and lowest in HS4, revealing higher stress of Hg in HS4 site. Overall, the outcomes of this field study broaden the information on seasonal trends of bioaccumulation of Hg and its toxic effects. These findings may be helpful in Hg monitoring and management programs in other river systems.

On-chip-based electrochemical biosensor for the sensitive and label-free detection of Cryptosporidium

Cryptosporidium, an intestinal protozoan pathogen, is one of the leading causes of death in children and diarrhea in healthy adults. Detection of Cryptosporidium has become a high priority to prevent potential outbreaks. In this paper, a simple, easy to fabricate, and cost-effective on-chip-based electrochemical biosensor has been developed for the sensitive and label-free detection of Cryptosporidium oocysts in water samples. The sensor was fabricated using standard lithography using a mask with a 3-electrode design and modified by self-assembling a hybrid of a thiolated protein/G and the specific anti-Cryptosporidium monoclonal antibodies (IgG3). The electrochemical impedance spectroscopy (EIS) was employed to quantitate C. parvum in the range of 0 to 300 oocysts, with a detection limit of approximately 20 oocysts/5 µL. The high sensitivity and specificity of the developed label-free electrochemical biosensor suggest that this novel platform is a significant step towards the development of fast, real-time, inexpensive and label-free sensing tool for early warning and immediate on-site detection of C. parvum oocysts in water samples, as compared to the traditional methods (such as PCR and microscopy). Furthermore, under optimized conditions, this label-free biosensor can be extended to detect other analytes and biomarkers for environmental and biomedical analyses.

An Improved Updatable Backpropagation Neural Network for Temperature Prognosis in Tunnel Fires

Because it is impossible to predict the temperature in advance, specific fire scenes (fire type, fire location, tunnel geometry, etc.) are unknown in traditional tunnel fire research. To address this difficulty, this work developed a novel algorithm to achieve temperature prognosis in tunnel fires that includes an updatable backpropagation (BP) neural network and a smoothing procedure. The data-driven algorithm is not limited to a specific fire scene, which makes it easy to fit real complex tunnel fire disasters. In addition, a full-scale fire test was conducted and utilized to verify the algorithm. Two innovations, including the updatable BP neural network and the smoothing procedure, made the predicted results match well with the experimental results. We can achieve a real-time precise temperature prediction 20 s in advance at a high accuracy of about 85.6%. If there is no sudden external factor intervention, the accuracy is about 99.4%. The algorithm provides an effective numerical tool for early fire warning and firefighting decision making that can address the temperature prognosis of tunnel fires.