Children in developing countries such as India will experience severe consequences of climate change. Primary school students, in particular, are the most vulnerable to extreme weather conditions, such as heat waves intensifying due to climate change. This will adversely impair their development, well-being, and learning outcomes. However, significant research gaps exist in understanding and mitigating children’s vulnerabilities. There is an urgent need for a deeper understanding of the impact of heat waves on children’s health and well-being in India. Further, the discussion on the state of heat safety in Indian primary schools is limited. This study addresses these gaps by surveying 335 primary school teachers in seven Indian cities. The data gathered from the field survey offers a better understanding of classroom experiences and challenges encountered by children and teachers during heat waves. It underscores several aspects of students’ vulnerability to heat exposure and its adverse impact on their health, such as absence from school, physical symptoms of heat distress, etc. Furthermore, it highlights the pressing need for classroom heat risk management in light of climate change and makes several policy prescriptions in primary schools.

Children differ from adults in their physiology and cognitive ability. Thus, they are extremely vulnerable to classroom thermal comfort. However, very few reviews on the thermal comfort of primary school students are available. Further, children-focused surveys have not reviewed the state-of-the-art in thermal comfort prediction using machine learning (AI/ML). Consequently, there is a need for discussion on children-specific challenges in AI/ML-based prediction. This article bridges these research gaps. It presents a comprehensive review of thermal comfort studies in primary school classrooms since 1962. It considers both conventional (non-ML) studies and the recent AI/ML studies performed for children, classrooms, and primary students. It also underscores the importance of AI/ML prediction by analyzing adaptive opportunities for children/students in classrooms. Thereafter, a review of AI/ML-based prediction studies is presented. Through an AI/ML case-study, it demonstrates that model performance for children and adults differs markedly. Performance of classification models trained on ASHRAE-II database and a recent primary students’ dataset shows a 29% difference in thermal sensation and 86% difference in thermal preference, between adults and children. It then highlights three major children-specific AI/ML challenges, viz., “illogical votes”, “multiple comfort metrics”, and “extreme class imbalance”. Finally, it offers several technical solutions and discusses open problems.

This study investigated children’s perceptions and adaptive behaviors related to indoor thermal conditions of classrooms in primary schools with no air-conditioning systems during both summer and winter in Dehradun City, Uttarakhand, India. Responses were collected from 5297 school children aged 6–13 years. During the measurement periods, 100% and 94% of the samples were obtained under conditions outside an 80% thermally acceptable comfort range in winter and summer, respectively. The analysis using receiver operating characteristics suggested that the students had the least sensitivity to the temperature variation for all scales of the thermal sensation vote (TSV). Approximately 95.1% of students were “very satisfied”, “satisfied”, or “slightly satisfied” with the thermal conditions under the condition of “extreme caution” or “danger” of heat risk. In contrast, adaptive thermal behaviors, such as adjusting clothing insulation ensembles, opening or closing classroom windows and doors, and utilizing ceiling fans, were found to be the most affordable options for optimizing indoor thermal comfort. Children’s reports of thermal sensations and thermal satisfaction did not correspond to the actual physical environment. This draws attention to the adequacy of applying widely used methods of TSV-based identification of the thermal comfort range in classrooms for children, especially in hot environments. The findings of this study are expected to serve as an evidence-based reference for local governments and authorities to take appropriate measures to mitigate heat risks for schoolchildren in the future.

Indoor thermal comfort immensely impacts the health and performance of occupants. Therefore, researchers and engineers have proposed numerous computational models to estimate thermal comfort (TC). Given the impetus toward energy efficiency, the current focus is on data-driven TC prediction solutions that leverage state-of-the-art machine learning (ML) algorithms. However, an occupant’s perception of indoor thermal comfort (TC) is subjective and multi-dimensional. Different aspects of TC are represented by various standard metrics/scales viz., thermal sensation (TSV), thermal comfort (TCV), and thermal preference (TPV). The current ML-based TC prediction solutions adopt the Single-task Learning approach, i.e., one prediction model per metric. Consequently, solutions often focus on only one TC metric. Moreover, when several metrics are considered, multiple ML models for a single indoor space lead to conflicting predictions, rendering real-world deployment infeasible. This work addresses these problems by leveraging Multi-task Learning for TC prediction in naturally ventilated buildings. First, a survey-and-measurement study is conducted in the composite climatic region of north India, in 14 naturally ventilated classrooms of 5 schools, involving 512 primary school students. Next, the dataset is analyzed for important environmental, physiological, and psycho-social factors that influence thermal comfort of children. Further, “DeepComfort”, a deep neural network based Multi-task Learning model is proposed. DeepComfort predicts multiple TC output metrics viz., TSV, TPV, and TCV, simultaneously through a single model. It is validated on ASHRAE-II database and the primary student dataset created in this study. It demonstrates high F1-scores, Accuracy (≈90%), and generalization capability, despite the challenges of illogical responses and data imbalance. DeepComfort is also shown to outperform 6 popular metric-specific single-task machine learning algorithms.

Classroom thermal comfort has a direct effect on student health and educational outcomes. However, measuring thermal comfort (TC) is a non-trivial task. It is represented by several subjective metrics e.g., Thermal Sensation Vote, Thermal Comfort Vote, Thermal Preference Vote, etc. Since machine learning (ML) is being increasingly used to predict occupant comfort, multiple TC metrics for the same indoor space may yield contradictory results. This poses the challenge of selecting the most suitable single TC metric or the minimal TC metric combination for a given indoor space. Ideally, it will be a metric that can be used to predict all other TC metrics and occupant behavior with high accuracy. This work addresses this problem by using a primary student thermal comfort dataset gathered from 11 schools and over 500 unique students. A comprehensive evaluation is carried out through hundreds of TC prediction models using several ML algorithms. It evaluates the ability of TC metrics to predict (a) other TC metrics, and (b) the adaptive behavior of primary students. An algorithm is proposed to select the most suitable single TC metric or the minimal TC metric input combination. Results show that ML models can accurately predict all TC metrics and occupant-adaptive behavior using a small subset of TC metrics with an average accuracy as high as 79%. This work also found Thermal Sensation Vote to be the most significant single TC predictor, followed by Thermal Satisfaction Level. Interestingly, satisfaction with clothing was found to be as equally relevant as thermal preference. Furthermore, the impact of seasons and choice of ML algorithms on TC metric and occupant behavior prediction is shown.

Rising global temperatures and heatwaves pose escalating health risks. This study aims to explore heatstroke (HS) awareness and prevention among 1142 residents of Fukuoka City, Japan, in 2020 and 2022. Questionnaire data revealed that while many respondents reported past experiences of HS-like symptoms (78.8%) and possessed high knowledge of HS symptoms (90.1%), only 56.3% adopted extensive (≥ 4) preventive measures. Crucially, a robust understanding of HS symptoms—rather than personal experience with mild symptoms—was the strongest predictor of adopting daily preventive practices (odds ratio [OR] 2.556, 95% confidence interval [CI] [1.715, 3.809], p < 0.001). The findings also highlight distinct challenges across demographics: older adults were more proactive in taking preventive measures, yet ensuring this translates to timely recognition of specific symptoms remains a key challenge. Conversely, younger individuals showed a significant behavioural gap, lagging in prevention despite frequent symptom experience. Notably, the adoption of preventive measures increased significantly in 2022 compared to 2020 (OR 2.808, p < 0.001), a change that coincided with the implementation of new national public health initiatives. These results underscore the need for tailored interventions, focusing on symptom recognition for older males and strategies to close the knowledge-behaviour gap among the young.