Evaluation of machine learning approaches for prediction of pigeon pea yield based on weather parameters in India.

Pigeon pea is the second most important grain legume in India, primarily grown under rainfed conditions. Any changes in agro-climatic conditions will have a profound influence on the productivity of pigeon pea (Cajanus cajan) yield and, as a result, the total pulse production of the country. In this context, weather-based crop yield prediction will enable farmers, decision-makers, and administrators in dealing with hardships. The current study examines the application of the stepwise linear regression method, supervised machine learning algorithms (support vector machines (SVM) and random forest (RF)), shrinkage regression approaches (least absolute shrinkage and selection operator (LASSO) or elastic net (ENET)), and artificial neural network (ANN) model for pigeon pea yield prediction using long-term weather data. Among the approaches, ANN resulted in a higher coefficient of determination (R2 = 0.88-0.99), model efficiency (0.88-1.00) with subsequent lower normalised root mean square error (nRMSE) during calibration (1.13-12.55%), and validation (0.33-21.20%) over others. The temperature alone or its interaction with other weather parameters was identified as the most influencing variables in the study area. The Pearson correlation coefficients were also determined for the observed and predicted yield. Those values also showed ANN as the best model with correlation values ranging from 0.939 to 0.999 followed by RF (0.955-0.982) and LASSO (0.880-0.982). However, all the approaches adopted in the study were outperformed the statistical method, i.e. stepwise linear regression with lower error values and higher model efficiency. Thus, these approaches can be effectively used for precise yield prediction of pigeon pea over different districts of Karnataka in India.

Prediction of mustard yield using different machine learning techniques: a case study of Rajasthan, India.

Mustard is the second most important edible oilseed after groundnut for India. Adverse weather drastically reduces the mustard yield. Weather variables affect the crop differently during different stages of development. Weather influence on crop yield depends not only on the magnitude of weather variables but also on weather distribution pattern over the crop growing period. Hence, developing models using weather variables for accurate and timely crop yield prediction is foremost important for crop management and planning decisions regarding storage, import, export, etc. Machine learning plays a significant role as it has a decision support tool for crop yield prediction. The models for mustard yield prediction was developed using long-term weather data during the crop growing period along with mustard yield data. Techniques used for developing the model were variable selection using stepwise multiple linear regression (SMLR) and artificial neural network (SMLR-ANN), variable selection using SMLR and support vector machine (SMLR-SVM), variable selection using SMLR and random forest (SMLR-RF), variable extraction using principal component analysis (PCA) and ANN (PCA-ANN), variable extraction using PCA and SVM (PCA-SVM), and variable extraction using PCA and RF (PCA-RF). Optimal combinations of the developed models were done for improving the accuracy of mustard yield prediction. Results showed that, on the basis of model accuracy parameters nRMSE, RMSE, and RPD, the PCA-SVM model performed best among all the six models developed for mustard yield prediction of study areas. Performance of mustard yield prediction done by optimum combinations of the models was better than the individual model.

Unraveling the dynamic impacts of COVID-19 on metro ridership: An empirical analysis of Beijing and Shanghai, China.

The outbreak of coronavirus disease 2019 (COVID-19) has had severely disruptive impacts on transportation, particularly public transit. To understand metro ridership changes due to the COVID-19 pandemic, this study conducts an in-depth analysis of two Chinese megacities from January 1, 2020, to August 31, 2021. Generalized linear models are used to explore the impact of the COVID-19 pandemic on metro ridership. The dependent variable is the relative change in metro ridership, and the independent variables include COVID-19, socio-economic, and weather variables. The results suggested the following: (1) The COVID-19 pandemic has a significantly negative effect on the relative change in metro ridership, and the number of cumulative confirmed COVID-19 cases within 14 days performs better in regression models, which reflects the existence of the time lag effect of the COVID-19 pandemic. (2) Emergency responses are negatively associated with metro system usage according to severity and duration. (3) The marginal effects of the COVID-19 variables and emergency responses are larger on weekdays than on weekends. (4) The number of imported confirmed COVID-19 cases only significantly affects metro ridership in the weekend and new-normal-phase models for Beijing. In addition, the daily gross domestic product and weather variables are significantly associated with metro ridership. These findings can aid in understanding the usage of metro systems in the outbreak and new-normal phases and provide transit operators with guidance to adjust services.

Modelling the impact of weather parameters on the microbial quality of water in distribution systems.

In this study, a framework for integrating weather variables and seasons into the modelling and prediction of the microbial quality in drinking water distribution networks is presented. Statistical analysis and Bayesian network (BN) modelling were used to evaluate relationships among water quality parameters in distribution pipes and their dependencies on weather parameters. Two robust predictive models for Total Bacteria in the network were built based on a deep learning approach (Long Short-Term Memory (LSTM)). The first model included water quality parameters alone as inputs while the second model included weather parameters. The seven-year dataset used in this study constituted water quality parameters measured at seven location in the water distribution network for the city of Ålesund in Norway, and weather data for the same period. Results of the initial statistical analysis and the BN models showed that, air temperature, the summer season, precipitation, as well as water quality parameters namely, residual chlorine, water temperature, alkalinity and electrical conductivity have strong relations with the counts of Total Bacteria in the distribution networks studied. It was found that the integration of the weather parameters in the Total Bacteria prediction models significantly improved the quality of the predictions. Compared to the LSTM 1, LSTM 2 achieved MAE and MSE values as high as to 6.8 and 4.9 times respectively when the model was tested on the seven locations. In addition, the R2 values were marginally higher in LSTM 2 (0.92-0.95) than in LSTM (0.81-0.86). The prediction results demonstrate the relevance of integrating weather parameters such as air temperature seasons in predicting bacteria levels in water distribution systems. This suggests that changes in the microbial quality of water in distribution systems and potentially drinking water sources could be reliably assessed by integrating online sensors of water quality and weather parameters with efficient models such as the LSTM. Applying this efficient modelling approach in the management of water supply systems could offer immense support in addressing current challenges in assessing the microbial quality of water and minimizing associated health risks.

Aeroallergens in North-Central Nigeria.

INTRODUCTION AND OBJECTIVES: Aeroallergens are airborne organic substances which are responsible for allergenic diseases in hypersensitive individuals. People are exposed to their allergens either directly or after their entrance into the interiors. The spatio-temporal pattern of aeroallergens and their relationship with weather variability in Abuja and Nassarawa, North-Central Nigeria was studied. MATERIALS AND METHODS: Aerosamples were trapped with modified Tauber-like pollen traps. Samples were collected monthly and centrifuged at 2500rpm for 5 min and subjected to acetolysis. Meteorological data were collected from the Nigerian Meteorological Agency. RESULTS AND CONCLUSION: Aeroallergens concentration were unequivocally regulated by weather variables in both locations, indicating the possible use of aeroallergens especially pollen and spores as bio-indicators of weather variations and change. Aeroallergens encountered were fungal spores, pollen, diatom frustules, fern spores, algal cyst/cells in decreasing order of dominance. Among pollen group, Poaceae, Amarathaceae/Chenopodiaceae and Hymenocardia acida dominated. Spores of Smut species, Puccinia, Curvularia and Nigrospora were major contributors among aeromycoflora. Fungal spores morphotype dominated during the rainier months and were major contributors of the aeroallergen spectrum with those belonging to Deuteromycete preponderant. Aeroallergens which were previously identified as triggers of conjunctivitis, asthma, allergic sinusitis and bronchopulmonary allergic diseases were frequently present in both locations. Pollen prevailed more during the harmattan, influenced by northeast trade wind. Pollen component differed and was based on autochthonous source plants, indicating difference in sub-vegetational types.

The impact of meteorological factors on involuntary admission in Attica, Greece.

Few studies in the literature have examined the effect of meteorological factors, especially temperature, on psychiatric hospitalization and even less on their association with involuntary admission. This study aimed to investigate the potential association of meteorological factors with the involuntary psychiatric hospitalization in the region of Attica, Greece. The research was conducted at the Psychiatric Hospital of Attica "Dafni". This was a retrospective time series study of 8 consecutive years of data (2010 to 2017) and included 6887 involuntarily hospitalized patients. Data on daily meteorological parameters were provided from the National Observatory of Athens. Statistical analysis was based on Poisson or negative binomial regression models with adjusted standard errors. Analyses were initially based on univariable models for each meteorological factor separately. All meteorological factors were taken into account through factor analysis and then, through cluster analysis, an objective grouping of days with similar weather type was performed. The resulting types of days were examined for their effect on the daily number of involuntary hospitalizations. Increases in maximum temperature, in average wind speed and in minimum atmospheric pressure values were associated with an increase in the average number of involuntary hospitalizations per day. Increase of the maximum temperature above 23 °C at lag 6 days before admission did not affect significantly the frequency of involuntary hospitalizations. Low temperature and average relative humidity above 60% levels had a protective effect. The predominant day type at lag 1 to 5 days before admission showed the strongest correlation with the daily number of involuntary hospitalizations. The cold season day type, with lower temperatures and a small diurnal temperature range, northerly winds of moderate speed, high atmospheric pressure and almost no precipitation, was associated with the lowest frequency of involuntary hospitalizations, whereas the warm season day type, with low daily temperature and small daily temperature range during the warm season, high values of relative humidity and daily precipitation, moderate wind speed/gust and atmospheric pressure, was associated with the highest. As climate change increases the frequency of extreme weather events, it is necessary to develop a different organizational and administrative culture of mental health services.

Coffee Berry Borer, Hypothenemus hampei (Ferrari) (Coleoptera: Curculionidae): Activity and Infestation in the High Mountain and Blue Mountain Regions of Jamaica.

Jamaica produces coffee marketed as Blue Mountain and high mountain (grown outside the Blue Mountains). Since the discovery of the coffee berry borer (CBB; Hypothenemus hampei) in Jamaica in 1978, chemical control has traditionally been the primary approach used to protect the crop from the pest. However, in the last 20 years, there has been an effort to shift towards more sustainable management strategies. The study was conducted to determine CBB activity (trap catch) and field infestation on coffee farms in the high mountains and Blue Mountains of Jamaica, over a crop cycle. A total of 27,929 and 12,921 CBBs were captured at high mountain and Blue Mountain farms, respectively. Peak CBB activity occurred in April in the high mountain region (365 CBBs/trap/month) and February in the Blue Mountain region (129 CBBs/trap/month). The highest levels of infestation were in November (33%) and October (34%) in the high mountain region and Blue Mountain region, respectively. There was no significant difference in the patterns of CBB activity and infestation between the study locations, and neither were related to the temperature or relative humidity. However, there was a significant relationship with rainfall. These data suggest that the population dynamics of the CBB may involve complex interactions among weather conditions, berry development, and agronomic practices.

Evaluation of sorghum genotypes and influence of weather variables on anthracnose (Colletotrichum sublineolum) disease development under field conditions at Jimma, southwestern Ethiopia.

The severity and temporal dynamics of sorghum anthracnose on six and nine sorghum genotypes were evaluated on field plots during 2014 and 2015 cropping years in Southwestern Ethiopia, respectively. Anthracnose severity was assessed as the proportion of leaf area affected by the disease. 12 consecutive time point anthracnose severity assessments and their mean severity, disease progress rate, AUDPC, grain yield and yield related components were used to evaluate the response of the genotypes. In the year 2014 and 2015, the mean anthracnose severity was varying from 65 to 79 PSI and 54-82 PSI among six and nine sorghum genotypes, respectively. AUDPC varied from 5063 to 6113%-day and 4171 to 6383%-day in the year 2014 and 2015, respectively. BRC-378 and BRC-245 genotypes consistently had the lowest disease levels and highest grain yields during the two experimental years. The disease pressure was reduced, whereas grain yield and 1000-seed weight of the genotypes were increased in 2015 cropping year. Anthracnose severity was strongly correlated with weather variables and showed strong negative associations with grain yield of all tested sorghum genotypes.

Distribution and Biodiversity of Seed-Borne Pathogenic and Toxigenic Fungi of Maize in Egypt and Their Correlations with Weather Variables.

Studies of the biodiversity of plant pathogenic and toxigenic fungi are attracting great attention to improve the predictability of their epidemics and the development of their control programs. Two hundred maize grain samples were gathered from 25 maize-growing governorates in Egypt and 189 samples were processed for the isolation and identification of seed-borne fungal microbiome. Twenty-six fungal genera comprising 42 species were identified according to their morphological characteristics and ITS DNA sequence analysis. Occurrence and biodiversity indicators of these fungal species were calculated. Ustilago maydis, Alternaria alternata, Aspergillus flavus, A. niger, Penicillium spp., Cladosporium spp. and Fusarium verticillioides were the highly frequent (>90% for each), recording the highest relative abundance (˃50%). Al-Menia governorate showed the highest species diversity and richness, followed by Sohag, Al-Nobaria and New Valley governorates. Correlations of 18 fungal species with temperature, relative humidity, precipitation, wind speed, and solar radiation were analyzed using canonical correspondence analysis. Results showed that relative humidity, temperature, and wind speed, respectively, were the most impactful weather variables. However, the occurrence and distribution of these fungi were not clearly grouped into the distinctive climatic regions in which maize crops are grown. Monitoring the occurrence and distribution of the fungal pathogens of maize grains in Egypt will play an important role in predicting their outbreaks and developing appropriate future management strategies. The findings in this study may be useful to other maize-growing countries that have similar climatic conditions.

Correlation between COVID-19 and weather variables: A meta-analysis.

Background: COVID-19 has significantly impacted humans worldwide in recent times. Weather variables have a remarkable effect on COVID-19 spread all over the universe. Objectives: The aim of this study was to find the correlation between weather variables with COVID-19 cases and COVID-19 deaths. Methods: Five electronic databases such as PubMed, Science Direct, Scopus, Ovid (Medline), and Ovid (Embase) were searched to conduct the literature survey from January 01, 2020, to February 03, 2022. Both fixed-effects and random-effects models were used to calculate pooled correlation and 95% confidence interval (CI) for both effect measures. Included studies heterogeneity was measured by Cochrane chi-square test statistic Q, I 2 and τ 2 . Funnel plot was used to measure publication bias. A Sensitivity analysis was also carried out. Results: Total 38 studies were analyzed in this study. The result of this analysis showed a significantly negative impact on COVID-19 fixed effect incidence and weather variables such as temperature (r = -0.113∗∗∗), relative humidity (r = -0.019∗∗∗), precipitation (r = -0.143∗∗∗), air pressure (r = -0.073∗), and sunlight (r = -0.277∗∗∗) and also found positive impact on wind speed (r = 0.076∗∗∗) and dew point (r = 0.115∗∗∗). From this analysis, significant negative impact was also found for COVID-19 fixed effect death and weather variables such as temperature (r = -0.094∗∗∗), wind speed (r = -0.048∗∗), rainfall (r = -0.158∗∗∗), sunlight (r = -0.271∗∗∗) and positive impact for relative humidity (r = 0.059∗∗∗). Conclusion: This meta-analysis disclosed significant correlations between weather and COVID-19 cases and deaths. The findings of this analysis would help policymakers and the health professionals to reduce the cases and fatality rate depending on weather forecast techniques and fight this pandemic using restricted assets.

Weather Variables Associated with Spore Dispersal of Lecanosticta acicola Causing Pine Needle Blight in Northern Spain.

In the last decade, the impact of needle blight fungal pathogens on the health status of forests in northern Spain has marked a turning point in forest production systems based on Pinus radiata species. Dothistroma needle blight caused by Dothistroma septosporum and D. pini, and brown spot needle blight caused by Lecanosticta acicola, coexist in these ecosystems. There is a clear dominance of L. acicola with respect to the other two pathogens and evidence of sexual reproduction in the area. Understanding L. acicola spore dispersal dynamics within climatic determinants is necessary to establish more efficient management strategies to increase the sustainability of forest ecosystems. In this study, spore counts of 15 spore traps placed in Pinus ecosystems were recorded in 2019 and spore abundance dependency on weather data was analysed using generalised additive models. During the collection period, the model that best fit the number of trapped spores included the daily maximum temperature and daily cumulative precipitation, which was associated to higher spore counts. The presence of conidia was detected from January and maximum peaks of spore dispersal were generally observed from September to November.

Interplay of weather variables in triggering the transmission of SARS-CoV-2 infection in Asia.

Weather variables are one of the crucial factors affecting respiratory infectious diseases; however, the effect of weather variables on the coronavirus disease 2019 (COVID-19) is still inconclusive and varies in different regions. The present study investigated the effects of weather variables (maximum temperature, MT; relative humidity, RH; wind speed, WS; precipitation, PR; and dew point, DP) on daily infection and death cases in three lockdown phases in Asia as of November 1, 2020. Generalized additive lag model was used to analyze the risk associated with weather variables, with confounders like median age of the national population, population density, country and lockdown phases. Our findings revealed that during lockdown phases all five weather variables show association with daily confirmed, and death cases. On the other hand, PR (pre-lockdown phase) and DP (lockdown phase) showed positive association with both daily confirmed  and death cases. Throughout the three lockdown phases MT, RH and PR showed strong positive associations with daily confimed/death cases. A lag period of 0-4-days possess higher risk of infection and death due to the varied ratios of different weather variables. The relative risk indicated that the infection and mortality risk was higher in India as compared to the rest of the countries. Here, unique combination of weather variables together with higher population density makes this region as one of the hotspots for COVID-19. This shows that the COVID-19 pandemic may be suppressed or enhanced with combination of different weather conditions together with factors like population density and median age of the country, which shall be useful for better implementation of health policies and further preparedness in Asia. Supplementary Information: The online version contains supplementary material available at 10.1007/s42398-021-00176-8.

DatAC: A visual analytics platform to explore climate and air quality indicators associated with the COVID-19 pandemic in Spain.

The coronavirus disease 2019 (COVID-19) pandemic has caused an unprecedented global health crisis, with several countries imposing lockdowns to control the coronavirus spread. Important research efforts are focused on evaluating the association of environmental factors with the survival and spread of the virus and different works have been published, with contradictory results in some cases. Data with spatial and temporal information is a key factor to get reliable results and, although there are some data repositories for monitoring the disease both globally and locally, an application that integrates and aggregates data from meteorological and air quality variables with COVID-19 information has not been described so far to the best of our knowledge. Here, we present DatAC (Data Against COVID-19), a data fusion project with an interactive web frontend that integrates COVID-19 and environmental data in Spain. DatAC is provided with powerful data analysis and statistical capabilities that allow users to explore and analyze individual trends and associations among the provided data. Using the application, we have evaluated the impact of the Spanish lockdown on the air quality, observing that NO2, CO, PM2.5, PM10 and SO2 levels decreased drastically in the entire territory, while O3 levels increased. We observed similar trends in urban and rural areas, although the impact has been more important in the former. Moreover, the application allowed us to analyze correlations among climate factors, such as ambient temperature, and the incidence of COVID-19 in Spain. Our results indicate that temperature is not the driving factor and without effective control actions, outbreaks will appear and warm weather will not substantially limit the growth of the pandemic. DatAC is available at https://covid19.genyo.es.

Seasonal variation in the allergenic potency of airborne grass pollen in Bratislava (Slovakia) urban environment.

The Phl p 5 allergen of the plant species Phleum pratense is considered one of the most crucial grass pollen allergenic molecules inducing respiratory allergies. In this study, we evaluated seasonal variation in the concentration of both grass pollen and Phl p 5 allergens as well as the ratio allergen/pollen (pollen potency) in the air of Bratislava during two consecutive years, 2019-2020. These 2 years differed in terms of air pollution, as COVID-19 lockdown in spring 2020 considerably improved air quality in the study area. Air samples were collected using a Hirst-type sampler for pollen detection and the cyclone sampler for aeroallergen detection. In 2020, we observed 80.3% higher seasonal pollen integral, probably associated with the longer pollen season duration, however, 43.6% lower mean daily pollen potency than in 2019. The mean daily pollen value was 37.5% higher in 2020 than in the previous year, while the mean daily allergen value was 14.9% lower in 2020. To evaluate the relationship between the amount of pollen or allergen in the air and selected meteorological factors and air pollution parameters, we used multiple regression analysis. Regarding weather factors, precipitation and relative humidity were significantly associated with pollen and/or allergen concentration, though these associations were negative. Atmospheric pollutants, especially CO, NO2 and O3 were significantly associated with pollen and/or allergen levels. The associations with CO and O3 were positive, while the association with NO2 was negative. Our results indicate that for grasses, an air pollutant that has a significant positive relationship to the ratio of allergen/pollen is nitrogen dioxide.

A review of the impact of weather and climate variables to COVID-19: In the absence of public health measures high temperatures cannot probably mitigate outbreaks.

The new severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) pandemic was first recognized at the end of 2019 and has caused one of the most serious global public health crises in the last years. In this paper, we review current literature on the effect of weather (temperature, humidity, precipitation, wind, etc.) and climate (temperature as an essential climate variable, solar radiation in the ultraviolet, sunshine duration) variables on SARS-CoV-2 and discuss their impact to the COVID-19 pandemic; the review also refers to respective effect of urban parameters and air pollution. Most studies suggest that a negative correlation exists between ambient temperature and humidity on the one hand and the number of COVID-19 cases on the other, while there have been studies which support the absence of any correlation or even a positive one. The urban environment and specifically the air ventilation rate, as well as air pollution, can probably affect, also, the transmission dynamics and the case fatality rate of COVID-19. Due to the inherent limitations in previously published studies, it remains unclear if the magnitude of the effect of temperature or humidity on COVID-19 is confounded by the public health measures implemented widely during the first pandemic wave. The effect of weather and climate variables, as suggested previously for other viruses, cannot be excluded, however, under the conditions of the first pandemic wave, it might be difficult to be uncovered. The increase in the number of cases observed during summertime in the Northern hemisphere, and especially in countries with high average ambient temperatures, demonstrates that weather and climate variables, in the absence of public health interventions, cannot mitigate the resurgence of COVID-19 outbreaks.

Statistical Modelling of the Effects of Weather Factors on Malaria Occurrence in Abuja, Nigeria.

Background: despite the increase in malaria control and elimination efforts, weather patterns and ecological factors continue to serve as important drivers of malaria transmission dynamics. This study examined the statistical relationship between weather variables and malaria incidence in Abuja, Nigeria. Methodology/Principal Findings: monthly data on malaria incidence and weather variables were collected in Abuja from the year 2000 to 2013. The analysis of count outcomes was based on generalized linear models, while Pearson correlation analysis was undertaken at the bivariate level. The results showed more malaria incidence in the months with the highest rainfall recorded (June-August). Based on the negative binomial model, every unit increase in humidity corresponds to about 1.010 (95% confidence interval (CI), 1.005-1.015) times increase in malaria cases while the odds of having malaria decreases by 5.8% for every extra unit increase in temperature: 0.942 (95% CI, 0.928-0.956). At lag 1 month, there was a significant positive effect of rainfall on malaria incidence while at lag 4, temperature and humidity had significant influences. Conclusions: malaria remains a widespread infectious disease among the local subjects in the study area. Relative humidity was identified as one of the factors that influence a malaria epidemic at lag 0 while the biggest significant influence of temperature was observed at lag 4. Therefore, emphasis should be given to vector control activities and to create public health awareness on the proper usage of intervention measures such as indoor residual sprays to reduce the epidemic especially during peak periods with suitable weather conditions.

Time, geography and weather provide insights into the ecological strategy of a migrant species.

Farmland and migratory bird populations are in decline. The Common quail (Coturnix coturnix) provides an exception to this trend and its populations have remained stable over the last two decades. However, some basic facts regarding quail biology and ecology, such as the geographic distribution of age and sex classes during the summer, remain poorly understood. We analyzed 43,194 Spanish quail ringing records from 1961 to 2014 to assess the effects of geography and weather conditions on the probability that individuals will be ringed during the various stages of their annual cycle (arrival -spring migration-, stationary breeding period, departure -autumn migration- and winter) for the different quail age-sex classes over time. We found that spatial distribution of the age and sex classes can be explained by date, latitude, longitude, altitude, rainfall, and temperature. Our results suggest that date accounts for most of the variation in the distribution of quail age classes, followed by the weather variables, and then latitude, and altitude. Similarly, date also accounts for most of the variation in the distribution of the two sexes. These results could partially explain why this species has avoided population decline, since its ecological strategy is based on its temporal and spatial distribution combined with the segregation of age and sex groups. We hypothesize that the distribution of quail age and sex classes follows variations in weather and habitat suitability to exploit seasonal and geographic variations in resource availability. The migratory and nomadic movements of quail, combined with the occurrence of multiple breeding attempts within a single season, may also allow these birds to overcome the impacts of predators and anthropogenic environmental change. Conservation and management efforts should therefore take account of these age and sex related temporal and spatial patterns.

Datasets on abundance of common blossom thrips and weather variables in small-scale avocado orchards at Taita Hills and Mount Kilimanjaro.

Avocado, Persea americana Miller (Lauraceae), is an important fruit crop cultivated by small-holder farmers along Afrotropical highlands of Taita Hills in South-eastern Kenya and Mount Kilimanjaro in Northern Tanzania. The small-holder farmers in these East African regions generate substantial food and cash from avocado fruits. However, the avocado crop is faced with challenges of infestation by insect pests such as the common blossom thrips (Frankliniella schultzei Trybom) which feeds on pollen and floral tissue thereby reducing productivity of the trees. Moreover, there is no information describing distribution patterns of Frankliniella schultzei and associated weather in East African avocado orchards despite the fact that small-scale farming is dependent on rainfall. This article was, therefore, initiated to provide dataset on abundance of Frankliniella schultzei from the avocado plants that relates with monthly rainfall and air temperatures at Taita Hills and Mount Kilimanjaro. Frankliniella schultzei was collected using white coloured beating tray and camel brush whereas air temperatures (°C) and rainfall (mm) was recorded daily using automatic data loggers and rain gauge, respectively. The survey at the two transects commenced during peak flowering season of avocado crop in August up to end of harvesting period in July of the following year. Temporal datasets were generated by Kruskal-Wallis Chi-square test. Current temporal datasets presents strong baseline information specifically for Kenya and Tanzania government agencies to develop further agricultural strategies aimed at improving avocado farming within Taita Hills and Mount Kilimanjaro agro-ecosystems.