Binary classification of rainfall time-series using machine learning algorithms

Summer monsoon rainfall contributes more than 75% of the annual rainfall in India. For the state of Maharashtra, India, this is more than 80% for almost all regions of the state. The high variability of rainfall during this period necessitates the classification of rainy and non-rainy days. While there are various approaches to rainfall classification, this paper proposes rainfall classification based on weather variables. This paper explores the use of support vector machine (SVM) and artificial neural network (ANN) algorithms for the binary classification of summer monsoon rainfall using common weather variables such as relative humidity, temperature, pressure. The daily data, for the summer monsoon months, for nineteen years, was collected for the Shivajinagar station of Pune in the state of Maharashtra, India. Classification accuracy of 82.1 and 82.8%, respectively, was achieved with SVM and ANN algorithms, for an imbalanced dataset. While performance parameters such as misclassification rate, F1 score indicate that better results were achieved with ANN, model parameter selection for SVM was less involved than ANN. Domain adaptation technique was used for rainfall classification at the other two stations of Maharashtra with the network trained for the Shivajinagar station. Satisfactory results for these two stations were obtained only after changing the training method for SVM and ANN.

Association of weather variables with the migration phenology and body conditions of Siberian warblers

Different elements of weather, such as wind speed, wind direction, precipitation and temperature are very important regulators of bird migration. Weather conditions also play role on the body condition such as body mass and the deposited fat. In this study we selected four warbler species to examine the impact of different weather variables on their spring and autumn migration timing and their body condition in one of the most extreme weather areas of the Earth, at Lake Baikal in Siberia. We also studied the changes in body mass and fat reserves during the spring and autumn migration periods of these species. For the analyses, we used ringing data of 2471 birds from five spring and five autumn seasons during 2015–2019. According to our results, it can be stated that the weather did not have a significant association with the migration timing of the studied warblers, perhaps due to the geographical location of the study site. However, the body mass and the fat reserves of the birds increased during unsuitable weather conditions because of the increased energy requirements. Birds generally migrate with low fat reserves, which is due to the fact that this area is not an important stopover site for these species.

Heritable and climatic sources of variation in juvenile tree growth in an Austrian common garden experiment of Central European Norway spruce populations

We leveraged publicly available data on juvenile tree height of 299 Central European Norway spruce populations grown in a common garden experiment across 24 diverse trial locations in Austria and weather data from the trial locations and population provenances to parse the heritable and climatic components of tree height variation. Principal component analysis of geospatial and weather variables demonstrated high interannual variation among trial environments, largely driven by differences in precipitation, and separation of population provenances based on altitude, temperature, and snowfall. Tree height was highly heritable and genetic variation for tree height was strongly associated with climatic relationships among population provenances. Modeling the covariance between populations and trial environments based on climatic data increased the heritable signal for tree height.

Extreme learning machines for weather-based modelling of silk cocoon production

In spite of the immense popularity and sheer power of the neural network models, their application in sericulture is still very much limited. With this backdrop, this study evaluates the suitability of neural network models in comparison with the linear regression models in predicting silk cocoon production of the selected six districts (Kolar, Chikballapur, Ramanagara, Chamarajanagar, Mandya and Mysuru) of Karnataka by utilising weather variables for ten consecutive years (2009-2018). As the weather variables are found to be correlated, principal components are obtained and fed into the linear (principal component regression) and non-linear models (back propagation-artificial neural network and extreme learning machine) as inputs. Outcomes emanated from this experiment have revealed the clear advantages of employing extreme learning machines (ELMs) for weather-based modelling of silk cocoon production. Application of ELM would be particularly useful, when the relation between production and its attributing characters is complex and non-linear.

Climate Change and Sustainability in Czech Wheat Production

The paper deals with the analysis of Czech wheat production and its determinants. We use the Just and Pope (1979) stochastic production function to estimate the effects of economic and weather variables, together with technological progress and climate change, on wheat yield in the Czech regions in the period 1961–2018. The results suggest that both economic and environmental factors play important roles in the wheat yield function. The output/input price ratio has a positive effect on the wheat yield. The effects of temperature and precipitation are month-specific and highly non-linear. Technological change also has a positive effect on yield, whereas climate change has a rather negative effect on wheat yield.

Abundance of sucking insect pests on some flowering plants in relation to weather parameters

The study was conducted from November 2017 to May 2018 in the experimental field at Gazipur, Bangladesh to investigate the incidence of sucking pests namely gladiolus thrips Teniothrips simplex, tuberose aphid Aphis craccivora, marigold aphid Neotoxoptera oliveri, and dahlia mealybug Plannococcus citri on their cultivated host plants in relation to temperature, relative humidity and rainfall. Results showed that the abundance of gladiolus thrips, tuberose aphid, marigold aphid and dahlia mealy bug reached the peak in the 3rd week of January, 3rd week of February, 1st week of January and 1st week of February, respectively. Among the weather factors, temperature had significant negative impact on the abundance of gladiolus thrips, marigold aphid and tuberose aphid, whereas rainfall showed significant negative influence only on marigold aphid. Multiple linear regression analysis showed that weather variables collectively predicted 55.9%, 75.9%, 44.5%, and 34.6% abundances of gladiolus thrips, marigold aphid, tuberose aphid and dahlia mealybug, respectively. Bangladesh J. Sci. Ind. Res.56(4), 241-248, 2021

Decades of Solar-driven geomagnetic disturbances impact homicide rates in Europe and the USA

Background: Homicides are the leading cause of death among young males. Conventional approaches to interpreting variations in criminality over time and across countries have failed to explain it.Methods: We applied ordinary least squared regressions on yearly homicide rates to identify the planetary drivers for homicides in Germany, the UK, and the USA over the past three solar cycles (22 to 24) between 1987 and 2018. We used the number of sunspots (solar activity), Kp and Ap indices (geomagnetic activity) from the National Oceanic and Atmospheric Administration (NOAA) and the German Research Centre for Geosciences DFZ-Potsdam, and weather variables from the countries’ meteorological organizations. Results: Our study revealed that lagged Kp NOAA index as a parameter of solar-driven geomagnetic disturbances (GMD) was the most important predictor to explain homicide rates in all three countries. Our results showed that over half the variance in homicide rates of all three countries could be attributed to GMD, not so by weather variables. We also predicted homicide rates peaking for 2025 and 2026 during the current 25th solar cycle, suggesting the current solar cycle could prove to be one of the most intense in a century, which would signal a concomitant increase in homicide rates. Based on the Italian experience in curbing homicides, we also suggest that collective agency may break what appears to be a deadly association between GMD and homicides.Conclusions: Our study suggests GMD may be involved in shaping human behavior and may help public and medical authorities prepare for eventual surges in homicides as the 25th solar cycle may induce stronger GMD.