The study, led by Hellen Naigaga of Uganda Martyrs University together with Runyararo Jolyn Rukarwa of RUFORUM and Joseph Ssekandi of Uganda Martyrs University, surveyed 384 respondents across the Bulambuli and Kapchorwa districts of the Mount Elgon region. The research team deliberately restricted participation to individuals aged 40 and above who had lived in their villages for at least 20 years, ensuring that respondents possessed the accumulated observational experience on which local ecological knowledge depends. Using a multi-stage stratified sampling design that moved from districts through counties and sub-counties down to households, the researchers interviewed farmers alongside district environment officers and district agriculture officers, who served as key informants.

The findings are striking in their breadth. Fully 88 percent of respondents demonstrated familiarity with plant species used to anticipate weather changes, and nearly all of those asked about awareness of such species reported knowing them. Knowledge proved remarkably uniform across demographic lines: chi-square tests of independence found no statistically significant association between phenological knowledge and gender, marital status, or occupation. The researchers interpret this as evidence that botanical weather forecasting is deeply embedded across the community rather than confined to a particular social group, a pattern consistent with the idea that indigenous climate knowledge is socially shared because of its direct relevance to household food security.

The indicators themselves follow clear physiological logic. Leaf shedding in species such as Cordia africana, Erythrina abyssinica, Milicia excelsa, and Ficus species signals an impending dry season, reflecting the water stress that trees experience as moisture becomes scarce. The emergence of new leaves and buds marks the transition toward rainfall, prompting farmers to prepare their gardens. Flowering adds a further layer of information: blossoms on Mangifera indica and Coffea species announce the start of the rainy season, and farmers even use the abundance and quality of the flowers to gauge how intense the coming rains will be. Cordia africana was the most frequently cited predictor, mentioned by 71 percent of respondents, followed by Erythrina abyssinica at 64 percent and Coffea species at 28 percent.

To test whether these local forecasts hold up empirically, the researchers compared community-reported rainy and dry months with meteorological data drawn from the TerraClimate dataset. The convergence was substantial. Farmers identified January as the driest month, with 98.7 percent agreeing, and April as the rainiest, cited by 87 percent. Both local knowledge and meteorological records pointed to April, May, September, October, and November as the wettest months. The only divergence involved minimal rainfall of less than 50 millimeters in January and December, which the instruments detect but farmers disregard, since drizzles of that magnitude have no bearing on farming decisions.

A Pearson correlation analysis comparing locally identified dry-spell months with monthly temperature records, used as a proxy for atmospheric dryness, revealed a positive relationship, with a correlation coefficient of 0.183. Although the correlation is modest and not statistically significant, with temperature explaining only about 3.4 percent of the variability, the direction of the trend indicates that community perceptions of dry spells rise in tandem with observed heat stress. The regression model, y = 4.1011x – 70.393, reinforces this positive tendency. In practical terms, farmers’ seasonal judgments track real atmospheric conditions closely enough to suggest genuine predictive value, even if the relationship is looser than a one-to-one correspondence.

The influence of phenological forecasting on farm management is profound. Planting time is the decision most governed by tree signals, with 93 percent of farmers relying on phenological changes to determine when to sow. Garden management followed at 71 percent, while food storage and harvesting decisions were influenced at 51 and 45 percent respectively. Land preparation, at 17 percent, depends more on labor and resource availability than on botanical cues. Farmers reported that this well-timed planning translates into tangible gains: 55 percent credited phenology-based scheduling with enabling timely planting, weeding, manuring, and pest control that help escape disease cycles and maximize resource use, while 22 percent attributed higher yields to careful planning combined with the soil fertility benefits of decomposed leaf litter from the very trees they monitor.

Knowledge of these indicators travels through an intricate web of social channels. Clan meetings, evening gatherings, family assemblies, circumcision ceremonies, drinking spots, church congregations, NGO-led trainings, and agricultural extension initiatives all serve as conduits for weather information, with village saving groups acting as particularly active hubs. This dense communication network matters for adaptation policy, the authors argue, because it shows that climate information in rural communities flows through existing socio-cultural structures rather than formal channels, and any effort to deliver improved forecasts must work with these systems rather than around them.

The broader context gives the findings urgency. Respondents consistently reported that the timing and reliability of rainy seasons have shifted away from historically stable calendars, injecting uncertainty into farming schedules across the region. Mount Elgon, with its humid subtropical climate, mean annual temperature of roughly 23 degrees Celsius, and rainfall averaging around 1,500 millimeters, has been among the Ugandan regions most intensely affected by climate change impacts. In settings where access to meteorological forecasts is limited, phenological indicators function as an accessible early warning system, and similar plant-based forecasting traditions have been documented from Indonesia to Tanzania, where Erythrina abyssinica and Ficus species serve comparable roles.

The study’s conclusions point toward integration rather than replacement. The authors recommend that conservation strategies prioritize the key indicator species, recognizing their dual ecological and informational value, and that meteorological institutions formally incorporate local phenological indicators into localized forecasting services to improve relevance, timeliness, and accessibility for smallholder farmers. They also call for community-based training programs that strengthen farmers’ capacity to interpret phenological signals alongside scientific forecasts, support intergenerational knowledge transmission, and institutionalize participatory research frameworks involving farmers, scientists, and policymakers. In a warming world where seasonal predictability is eroding, the trees of Mount Elgon suggest that the most resilient forecast may be one written jointly by satellites and leaves.

Subject of Research: Indigenous plant-phenology knowledge for anticipating seasonal weather changes among smallholder farmers in Uganda's Mount Elgon region

Article Title: Integrating local plant-phenology knowledge into anticipating seasonal weather changes: evidence from smallholder farmers in Uganda’s Mount Elgon region (cross-sectional survey)

Article References: Naigaga, H., Rukarwa, R. J., & Ssekandi, J. (2026). Integrating local plant-phenology knowledge into anticipating seasonal weather changes: evidence from smallholder farmers in Uganda’s Mount Elgon region (cross-sectional survey). BMC Environmental Science, 3(1), Article 11. https://doi.org/10.1186/s44329-026-00052-y

Image Credits: AI Generated

DOI: 10.1186/s44329-026-00052-y

Keywords: plant phenology, indigenous knowledge, weather forecasting, smallholder farmers, Mount Elgon, Uganda, climate change adaptation, Cordia africana, Erythrina abyssinica, meteorological data, seasonal rainfall, agricultural decision-making

The stakes could hardly be higher. Air pollution alone contributes to an estimated 4.2 million premature deaths each year, with the burden falling disproportionately on low- and middle-income countries. Mortality risk rises by 10 to 25 percent for every degree Celsius above regional temperature thresholds, and heat-related deaths among adults aged 65 and over have surged by 167 percent compared with the 1990s, a rise that exceeds what demographic ageing alone can explain. Across Europe, an estimated 368,183 heat-related deaths occurred between 2010 and 2022, 89 percent of them among people aged 65 or older. Children, whose thermoregulation is still immature, and people living with mental health conditions or long-term illness face elevated risks from heat, cold spells, and flooding alike.

What makes meteorological data so difficult for traditional statistics is that the atmosphere behaves as a unified physical-chemical continuum in which one variable drives another. During temperature inversions or atmospheric blocking events, suppressed boundary layer mixing can allow particulate matter to accumulate at the surface while ozone levels remain largely unaffected. Inhaled particles then travel through the airways, triggering systemic inflammation, oxidative stress from free radicals, and cardiac and neurological damage as toxins enter the bloodstream. These relationships are non-linear, spatio-temporally complex, and conditional on interactions between variables, which means the very signals that drive weather-related health risks can be excluded from conventional models such as generalised additive models that have historically defined climate-health research.

This is precisely where machine learning enters the picture. AI methods can automatically handle non-linear relationships and spatio-temporal structures without manual model specification, and hybrid models combining physical and data-driven approaches have demonstrated improved forecasting accuracy, better detection of extreme weather events, and reduced systematic biases compared with traditional numerical weather prediction. AI-assisted systems can also improve downscaling, resolving fine-scale atmospheric structures by balancing multi-scale constraints. In principle, this positions AI to map how specific cascading climate states trigger downstream morbidity and mortality through a domino effect, offering a granularity that classical statistics cannot match.

To understand how this potential is being realised, the Southampton team conducted a rapid review following PRISMA-RR guidelines, searching PubMed, Web of Science, and Scopus for peer-reviewed studies published between January 2020 and October 2025. Two reviewers independently screened 876 identified records, ultimately including twelve studies that applied AI tools to meteorological data in human health research. The team deliberately imposed no prespecified definition of artificial intelligence, including any article in which the term was explicitly stated, a decision that itself reflects how heterogeneously the label is applied across the literature.

The twelve studies were strikingly diverse. Eight were observational, with the remainder experimental, longitudinal, or retrospective cohort designs. Sample sizes ranged from just 12 participants to more than 10 million, and data collection periods varied from 20 minutes to 11 years. Six studies were conducted in high-income countries with temperate climates, while the rest took place in middle- to low-income settings with extreme climates, including Bangladesh, China, Kenya, Mali, and Vietnam, where weather-related health risks are generally more acute. The most common meteorological variables were air quality, including particulate matter, and temperature, each appearing in six studies, followed by humidity and rainfall, pressure and wind, and seasonality. Ground stations and air sensors were used in every study, and seven also incorporated satellite data.

Health outcomes clustered around respiratory disease such as asthma and chronic obstructive pulmonary disease, which appeared in six studies, and bacterial or viral illness such as diarrhoea, which appeared in four. The remainder examined heat-related illness, migraine and headaches, COVID-19, febrile illness including dengue, and cardiovascular disease. On the technical side, Random Forest and other decision-tree methods dominated, appearing in five studies, followed by time-series and clustering analyses, regression, gradient boosting, and multivariate or multilayer approaches. Model performance was most commonly evaluated using sensitivity, though four studies specified no performance metrics at all, and metrics such as area under the curve, specificity, and predictive capability appeared inconsistently across the set.

The headline finding was encouraging: in study after study, incorporating meteorological variables improved the predictive value of the models. Random Forest analyses showed that adding air pollution and seasonality sharpened predictions of increased prevalence and severity of diarrhoea, dyspnoea, COVID-19, asthma, and pneumonia. Time-series and gradient boosting approaches found that temperature, humidity, air pressure, wildfire smoke, and seasonality similarly enhanced predictions of respiratory, cardiovascular, heat-related, febrile, and headache conditions. Regression and unspecified machine learning methods linked rainfall, pollution, and temperature extremes to bronchitis and even vaginal bacterial composition. Yet a clear association between the AI technique used, the meteorological variable integrated, and the health outcome addressed emerged only for the well-established link between pollution and respiratory disease.

Beneath the encouraging results, however, the review uncovered a troubling pattern of underreporting. In seven of the twelve studies, the reasoning behind the choice of AI tool or performance metric was simply absent, leaving the added benefit of machine learning over conventional statistics unclear. Explainable AI appeared in only one study, despite techniques such as Shapley additive explanations, local interpretable model-agnostic explanations, and permutation feature importance being available to unpack black-box models. More worryingly, ethnicity was reported in only one study, and the review’s authors note that many excluded studies failed to record even basic sample sizes, suggesting the true scale of AI-driven climate-health research is far larger than the twelve studies captured. The absence of demographic detail likely degrades model performance and risks exacerbating existing health inequities, particularly for older adults and people with mental health or long-term conditions who are most vulnerable to weather-induced illness but least represented in the training data.

The review’s conclusions are a call to order for a field that could reshape public health preparedness. The authors recommend integrating explainable AI frameworks such as SHAP and LIME to transparently map non-linear interactions between meteorological variables and health outcomes, enforcing the reporting of age, sex, ethnicity, and socioeconomic status to prevent algorithmic bias, and requiring clear rationales for the selection of machine learning tools and performance metrics. They also urge energy-efficient AI designs combined with real-time climate data and physics-based standards, noting that the computational demands of AI carry their own environmental footprint through greenhouse gas emissions and electronic waste. Done well, AI-driven modelling of meteorological data could enable targeted interventions that prevent hospitalisation and premature death as climate change intensifies; done carelessly, it could produce opaque, biased tools that deepen the very inequities they are meant to address. The technology, the review makes clear, is ready. The reporting standards are not, and closing that gap is now the field’s most urgent task.

Subject of Research: The application of artificial intelligence to meteorological data for predicting weather-related health outcomes

Article Title: Application of Artificial Intelligence in analysing meteorological data for health research: A rapid review

Article References: Michels, L. V., Smith, L., Ghannam, S., Gadd, C., & Dambha-Miller, H. (2026). Application of Artificial Intelligence in analysing meteorological data for health research: A rapid review. Air Quality, Atmosphere & Health, 19(9), Article 201. https://doi.org/10.1007/s11869-026-02085-3

Image Credits: AI Generated

DOI: 10.1007/s11869-026-02085-3

Keywords: artificial intelligence, machine learning, meteorological data, climate change, public health, air pollution, Random Forest, predictive modelling, respiratory disease, explainable AI, heat-related mortality, health equity