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.

Sustainability assessment of crops' production in India: empirical evidence from ARDL-ECM approach

PurposeThe study aims to evaluate the long- vs short-run relationships between crops' production (output) and crops' significant inputs such as land use, agricultural water use (AWU) and gross irrigated area in India during the period 1981–2018.Design/methodology/approachThe study applied the autoregressive distributed lag (ARDL) bounds testing approach to estimate the co-integration among the variables. The study uses the error correction model (ECM), which integrates the short-run dynamics with the long-run equilibrium.FindingsThe ARDL bounds test of co-integration confirms the strong evidence of the long-run relationship among the variables. Empirical results show the positive and significant relationship of crops' production with land use and gross irrigated area. The statistically significant error correction term (ECT) validates the speed of adjustment of the empirical models in the long-run.Research limitations/implicationsThe study suggests that the decision-makers must understand potential trade-offs between human needs and environmental impacts to ensure food for the growing population in India.Originality/valueFor a clear insight into the impact of climate change on crops' production, the current study incorporates the climate variables such as annual rainfall, maximum temperature and minimum temperature. Further, the study considered agro-chemicals, i.e. fertilizers and pesticides, concerning their negative impacts on increased agricultural production and the environment.

Analysis of rainfall trends over Tripura

Rainfall in India has very high temporal and spatial variability. The rainfall variability affects the livelihood and food habits of people from different regions. In this study, the rainfall trends in two stations in the north-eastern state of Tripura, namely Agartala and Kailashahar have been studied for the period 1955-2017. The state experiences an annual mean of more than 2000 mm of rainfall, out of which, about 60% occurs during the monsoon season and about 30% in pre-monsoon. An attempt has been made to analyze the trends in seasonal and annual rainfall, rainy days and heavy rainfall in the two stations, during the same period.Non-parametric Mann-Kendall test has been used to find out the significance of these trends. Both increasing and decreasing trends are observed over the two stations. Increasing trends in rainfall, rainy days and heavy rainfall are found at Agartala during pre-monsoon season and decreasing trends in all other seasons and at annual scale. At Kailashahar, rainfall amount (rainy days & heavy rainfall) is found to be increasing during pre-monsoon and monsoon seasons (pre-monsoon season). At annual scale also, rainfall and rainy days show increasing trends at Kailashahar. The parameters are showing decreasing trends during all other seasons at the station. Rainy days over Agartala show a significantly decreasing trend in monsoon, whereas no other trend is found to be significant over both the stations.

Impact of climate change on domestic water accessibility in Bamenda III Sub-Division, North West region, Cameroon

The effects of climate change are felt most at the household level, when taps and springs run dry for several weeks or months, forcing people to access potable water from doubtful sources. There has been an increase in the population of Bamenda III without a proportionate increase in the water supply capacity. This has resulted in severe water crises, even though Bamenda III municipality has water supplies from the Council, Community, CAMWATER, natural springs and streams, wells and boreholes. Household data on water accessibility against a backdrop of a changing climate was collected using 269 questionnaires to assess perceptions on the state of water resources and climate. Rainfall data were collected from 1963-2019 and results revealed that mean annual rainfall is at 182.52 mm, with a standard deviation of 29.16 and a Coefficient of Variation of 15.69%, while the mean Standardized Precipitation Index is -0.07 (mild dryness), and rainfall has reduced by -2.07 mm from 1963-2019. The population attributed problems of water accessibility to climate change, urbanization and poor water governance. It is recommended that sustainable water management through Nature-based Solutions and Ecosystem-based Adaptation should be implemented from the watershed to the community level.

The Relationship between Climate Change, Variability, and Food Security: Understanding the Impacts and Building Resilient Food Systems in West Pokot County, Kenya

This study integrated local and scientific knowledge to assess the impacts of climate change and variability on food security in West Pokot County, Kenya from 1980–2012. It characterized rainfall and temperature from 1980–2011 and the phenology of agricultural vegetation, assessed land use and land cover (LULC) changes, and surveyed local knowledge and perceptions of the relationships between climate change and variability, land use decisions, and food (in)security. The 124 respondents were aware of long-term changes in their environment, with 68% strongly believing that climate has become more variable. The majority of the respondents (88%) reported declining rainfall and rising temperatures, with respondents in the lowland areas reporting shortened growing seasons that affected food production. Meteorological data for 1980–2011 confirmed high inter-annual rainfall variability around the mean value of 973.4 mm/yr but with no notable trend. Temperature data showed an increasing trend between 1980 and 2012 with lowlands and highlands showing changes of +1.25 °C and +1.29 °C, respectively. Land use and land cover changes between 1984 and 2010 showed cropland area increased by +4176% (+33,138 ha), while grassland and forest areas declined by –49% (–96,988 ha) and –38% (–65,010 ha), respectively. These area changes illustrate human-mediated responses to the rainfall variability, such as increased stocking after good rainfall years and crop area expansion. The mean Normalized Difference Vegetation Index (NDVI) values ranged from 0.36–0.54 within a year, peaking in May and September. For weather-related planning, respondents relied on radio (64%) and traditional forecasters (26%) as predominant information sources. Supporting continuous climate change monitoring, intensified early warning systems, and disseminating relevant information to farmers could help farmers adopt appropriate adaptation strategies.

Drought: A Common Environmental Disaster

Droughts have been identified as an environmental hazard by environmentalists, ecologists, hydrologists, meteorologists, geologists, and agricultural experts. Droughts are characterised by a decrease in precipitation over a lengthy period, such as a season or a year, and can occur in virtually all climatic zones, including both high and low rainfall locations. This study reviewed drought-related impacts on the environment and other components particularly, in South Africa. Several attempts have been made using innovative technology such as earth observation and climate information as recorded in studies. Findings show that the country is naturally water deficient, which adds to the climate fluctuation with the average annual rainfall in South Africa being far below the global average of 860 mm per year. Drought in South Africa’s Western Cape Province, for example, has resulted in employment losses in the province’s agriculture sector. According to the third quarterly labor force survey from 2017, the agricultural industry lost almost 25,000 jobs across the country. In the Western Cape province, about 20,000 of these were lost which has a direct impact on income generation. Many of these impacts were linked to drought events.

Global prevalence and epidemiology of Strongyloides stercoralis in dogs: a systematic review and meta-analysis

Background Strongyloides stercoralis, a soil-transmitted helminth, occurs in humans, non-human primates, dogs, cats and wild canids. The zoonotic potential between these hosts is not well understood with data available on prevalence primarily focused on humans. To increase knowledge on prevalence, this review and meta-analysis was performed to estimate the global status of S. stercoralis infections in dogs. Methods Following the PRISMA guidelines, online literature published prior to November 2020 was obtained from multiple databases (Science Direct, Web of Science, PubMed, Scopus and Google Scholar). Prevalence was calculated on a global and country level, by country income and climate, and in stray/animal shelter dogs versus owned dogs. Statistical analyses were conducted using R-software (version 3.6.1). Results From 9428 articles, 61 met the inclusion criteria. The estimated pooled global prevalence of S. stercoralis in dogs was 6% (95% CI 3–9%). Infection was found to be the most prevalent in low-income countries with pooled prevalence of 22% (95% CI 10–36%). The highest pooled prevalence of S. stercoralis in dogs was related to regions with average temperature of 10–20 °C (6%; 95% CI 3–11%), an annual rainfall of 1001–1500 mm (9%; 95% CI 4–15%) and humidity of 40–75% (8%; 95% CI 4–13%). Prevalence was higher in stray and shelter dogs (11%; 95% CI 1–26%) than in owned dogs (3%; 95% CI 1–7%). Conclusions As with S. stercoralis in humans, higher prevalence in dogs is found in subtropical and tropical regions and lower-income countries, locations which also can have high dog populations. While this study presents the first estimated global prevalence of S. stercoralis in dogs, it is potentially an underestimation with 15 of 61 studies relying on diagnostic methods of lower sensitivity and a paucity of data from most locations. Standardized protocols (e.g. quantity of feces and number of samples for a Baermann) in future studies could improve reliability of results. More prevalence studies and raising veterinary awareness of S. stercoralis are needed for a One Health approach to protect humans and dogs from the impact of the infection. Graphical Abstract

Assessment of PERSIANN-CCS, PERSIANN-CDR, SM2RAIN-ASCAT, and CHIRPS-2.0 Rainfall Products over a Semi-Arid Subtropical Climatic Region

This study compares the performance of four satellite-based rainfall products (SRPs) (PERSIANN-CCS, PERSIANN-CDR, SM2RAIN-ASCAT, and CHIRPS-2.0) in a semi-arid subtropical region. As a case study, Punjab Province of Pakistan was considered for this assessment. Using observations from in-situ meteorological stations, the uncertainty in daily, monthly, seasonal, and annual rainfall estimates of SRPs at pixel and regional scales during 2010–2018 were examined. Several evaluation indices (Correlation Coefficient (CC), Root Mean Square Error (RMSE), Bias, and relative Bias (rBias), as well as categorical indices (Probability of Detection (POD), Critical Success Index (CSI), and False Alarm Ration (FAR)) were used to assess the performance of the SRPs. The following findings were found: (1) CHIRPS-2.0 and SM2RAIN-ASCAT products were capable of tracking the spatiotemporal variability of observed rainfall, (2) all SRPs had higher overall performances in the northwestern parts of the province than the other parts, (3) all SRP estimates were in better agreement with ground-based monthly observations than daily records, and (4) on the seasonal scale, CHIRPS-2.0 and SM2RAIN-ASCAT were better than PERSIANN-CCS and PERSIANN. In all seasons, CHIRPS-2.0 and SM2RAIN-ASCAT outperformed PERSIANN-CCS and PERSIANN-CDR. Based on our findings, we recommend that hydrometeorological investigations in Pakistan’s Punjab Province employ monthly estimates of CHIRPS-2.0 and SM2RAIN-ASCAT products.

On some aspects of southwest monsoon rainfall over Tamilnadu

The rainfall during southwest monsoon season over Tamilnadu is quite significant from the point of view of water storage in major reservoirs as northeast monsoon rainfall, which is about half of the annual rainfall, is not stable enough due to its large interannual variability. The southwest monsoon rainfall, on the other hand, is more stable. The north-south oriented trough over Tamilnadu and adjoining Bay togetherwith upper air cyclonic circulation/trough in lower tropospheric levels account for three fourths of significant rainfall occurrence during southwest monsoon season. Rainfall during southwest monsoon and northeast monsoon seasons was found to be independent with a small negative correlation of -0.18. This shows that the southwest monsoon rainfall may not be of much use to predict the pattern of northeast monoon rainfall over Tamilnadu.

Climate Change Effects, Adaptation, and Mitigation Techniques in Tropical Dry Forests

Tropical dry forests is one of the most unique forest types. It differs from other tropical forests with its climatic behavior like a prominent dry period, little annual rainfall, and high evapotranspiration. Out of six global bioclimatic zones, the forests are distributed in four. Climate change is now the most challenging issue regarding the fate of tropical dry forests. A severe climatic change is estimated to occur between 2040 and 2069 that could drastically change the precipitation pattern, temperature, aridity, and distribution of biodiversity. It could alter the forest type permanently. With a large number of heat-tolerant species, tropical dry forests have a great potentiality to conservationists with the prediction of a large area that could attain the climatic condition favorable for extension of tropical dry forests. But many of the species of tropical dry forests could be extinct due to changing climate at the same time. Proper adaptation and mitigation techniques could minimize the severity of climate change effects.