International Journal of Big Data Mining for Global Warming

Carbon footprint analysis for different freshwater aquaculture practices in different states of India along with Bay of Bengal was done. In West Bengal, the average inputs as carbon equivalent (CE) were $1936\pm 868$kg/ha with an average output of $5263\pm 2041$kg live weight/ha. In Odisha, the inputs as CE were $2049\pm 1638$kg/ha with an output of $3028\pm 2059$kg live weight/ha. In Andhra Pradesh, the average inputs as CE was $3889\pm 980$kg/ha with an average output of $8314\pm 2171$kg live weight/ha for Litopenaeus vannamei culture practices, while the same for Indian major carps culture was $5806\pm 2380$kg/ha with an output of $10179\pm 3111$kg live weight/ha, respectively. The average Global Warming Potential (GWP) of all the carp culture practices in different study places was 1.57kg CO₂-e/kg fish, while the same for $L.$ vannamei culture was 1.87kg CO₂-e/kg shrimp.

This paper is about the problem of drought and its future. The research methods are both theoretical and field studies. This paper presents a mathematical model for drought analysis in Australia that can predict its future trend. It analyses three meteorological indicators, including annual rainfall, increases in temperature, and water consumption volume. Surveys about the mentioned indicators are from the past to the present and now to the future intervals. This paper suggests practical solutions to change the conditions of drought-affected regions. The research method, simulated exemplary, and outcomes of this paper are applicable everywhere in the world affected by the hydro-drought crisis.

Climate change and water scarcity may badly affect existing rice production system in Bangladesh. With a view to sustain rice productivity and mitigate yield scaled CH₄ emission in the changing climatic conditions, a pot experiment was conducted under different soil water contents, biochar and silicate amendments with inorganic fertilization (NPKS). In this regard, 12 treatments combinations of biochar, silicate and NPKS fertilizer along with continuous standing water (CSW), soil saturation water content and field capacity (100% and 50%) moisture levels were arranged into rice planted potted soils. Gas samples were collected from rice planted pots through Closed Chamber technique and analyzed by Gas Chromatograph. This study revealed that seasonal CH₄ emissions were suppressed through integrated biochar and silicate amendments with NPKS fertilizer (50–75% of the recommended doze), while increased rice yield significantly at different soil water contents. Biochar and silicate amendments with NPKS fertilizer (50% of the recommended doze) increased rice grain yield by 10.9%, 18.1%, 13.0% and 14.2%, while decreased seasonal CH₄ emissions by 22.8%, 20.9%, 23.3% and 24.3% at continuous standing water level (CSW) (T9), at saturated soil water content (T10), at 100% field capacity soil water content (T11) and at 50% field capacity soil water content (T12), respectively. Soil porosity, soil redox status, SOC and free iron oxide contents were improved with biochar and silicate amendments. Furthermore, rice root oxidation activity (ROA) was found more dominant in water stress condition compared to flooded and saturated soil water contents, which ultimately reduced seasonal CH₄ emissions as well as yield scaled CH₄ emission. Conclusively, soil amendments with biochar and silicate fertilizer may be a rational practice to reduce the demand for inorganic fertilization and mitigate CH₄ emissions during rice cultivation under water stress drought conditions.

The coarse horizontal resolution global climate models (GCMs) have limitations in producing large biases over the mountainous region. Also, single model output or simple multi-model ensemble (SMME) outputs are associated with large biases. While predicting the rainfall extreme events, this study attempts to use an alternative modeling approach by using five different machine learning (ML) algorithms to improve the skill of North American Multi-Model Ensemble (NMME) GCMs during Indian summer monsoon rainfall from 1982 to 2009 by reducing the model biases. Random forest (RF), AdaBoost (Ada), gradient (Grad) boosting, bagging (Bag) and extra (Extra) trees regression models are used and the results from each models are compared against the observations. In simple MME (SMME), a wet bias of 20mm/day and an RMSE up to 15mm/day are found over the Himalayan region. However, all the ML models can bring down the mean bias up to $\pm 1.5$mm/day and RMSE up to 2mm/day. The interannual variability in ML outputs is closer to observation than the SMME. Also, a high correlation from 0.5 to 0.8 is found between in all ML models and then in SMME. Moreover, representation of RF and Grad is found to be best out of all five ML models that represent a high correlation over the Himalayan region. In conclusion, by taking full advantage of different models, the proposed ML-based multi-model ensemble method is shown to be accurate and effective.