Machine learning ensembles, neural network, hybrid and sparse regression approaches for weather based rainfed cotton yield forecast.

Cotton is a major economic crop predominantly cultivated under rainfed situations. The accurate prediction of cotton yield invariably helps farmers, industries, and policy makers. The final cotton yield is mostly determined by the weather patterns that prevail during the crop growing phase. Crop yield prediction with greater accuracy is possible due to the development of innovative technologies which analyses the bigdata with its high-performance computing abilities. Machine learning technologies can make yield prediction reasonable and faster and with greater flexibility than process based complex crop simulation models. The present study demonstrates the usability of ML algorithms for yield forecasting and facilitates the comparison of different models. The cotton yield was simulated by employing the weekly weather indices as inputs and the model performance was assessed by nRMSE, MAPE and EF values. Results show that stacked generalised ensemble model and artificial neural networks predicted the cotton yield with lower nRMSE, MAPE and higher efficiency compared to other models. Variable importance studies in LASSO and ENET model found minimum temperature and relative humidity as the main determinates of cotton yield in all districts. The models were ranked based these performance metrics in the order of Stacked generalised ensemble > ANN > PCA ANN > SMLR ANN > LASSO> ENET > SVM > PCA SMLR > SMLR SVM > SMLR. This study shows that stacked generalised ensembling and ANN method can be used for reliable yield forecasting at district or county level and helps stakeholders in timely decision-making.

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.

Application of homobrassinolide enhances growth, yield and quality of tomato.

Brassinosteroids (BRs) have emerged as pleiotropic phytohormone owing to their wide function in crop growth and metabolism. Homobrassinolide (HBR) being an analogue of BRs is known to improve the growth, yield and quality parameters in many crop plants. Thus, an evaluation study was conducted for two years (2018 and 2019) to elucidate the performance of tomato plants (Solanum lycopersicum L.) to a novel group of phytohormone,HBR. The field experiment comprised of seven treatments with homobrassinolide 0.04% (Emulsifiable Concentrate) EC at four different concentrations (0.06, 0.08, 0.10 and 0.12 g active ingredient (a.i.) ha-1) and two well-known growth promoters viz., Gibberellic acid (GA), Naphthalene Acetic Acid (NAA) along with the untreated control. Plant height and chlorophyll concentration were found significantly different in both years of experiment as well as among the different treatments. HBR at 0.12 g a.i. ha-1 was found better with maximum number of fruits (77.36 plant-1), fruit length (6.72 cm), fruit breadth (6.45 cm) and fruit weight (80.52 g) over other concentrations and treatments. Fruit yield was more pronounced in the plots treated with plant growth regulators compared to untreated control. However, significantly higher fruit yield of 91.07 t ha-1 (62.58 t ha-1 with untreated control) along with improved quality traits viz., fruit firmness (4.11 kg cm-2), ascorbic acid content (24.09 mg 100 g-1), total soluble solids (4.43°Brix) and keeping quality (12.50 days) was recorded in 0.12 g a.i. ha-1 HBR treated plots. Thus, it can be inferred that HBRapplication would be a better option to enhance growth, yield as well as quality traits in tomato.

Influence of sowing windows and genotypes on growth, radiation interception, conversion efficiency and yield of guar.

Crop growth largely depends on radiation. Radiation is the main impetus for photosynthesis and movement of photosynthates from source to sink. Therefore, identification of the optimum sowing windows and suitable cultivars for efficient utilization of radiation is of prime importance. A field study was conducted in red clay soil during 2014 and 2015 Kharif season and the treatments consisted of three genotypes and three sowing windows by using randomized complete block design with three replications. The effect of genotypes and sowing windows was found significant with respect to number of trifoliate leaves, leaf area ratio, dry matter production, grain numbers, pod length, test weight, grain yield, and stover yield of guar during 2014 as compared to 2015 sown crop. Statistically significant plant height, number of trifoliate leaves, number of branches, leaf area ratio, absolute growth rate, leaf area index, dry matter, grain number, pod length, grain yield, stover yield and a higher cumulative radiation interception were recorded with 15th August sown crop as compared to other sowing windows. The plant height, number of trifoliate leaves, number of branches, leaf area ratio, absolute growth rate, leaf area index, dry matter, grain number, pod length, grain yield, stover yield and maximum cumulative interception of radiation were significant with RGC-1003 as compared to RGC-936 and HG-365. It is observed that the incident PAR to dry matter accumulation conversion efficiency was varied with cultivars and different sowing windows which ranges from 0.74 g MJ-1 to 0.79 g MJ-1.

Assessing the Impact of Higher Levels of CO2 and Temperature and Their Interactions on Tomato (Solanumlycopersicum L.).

Climate change has increasing effects on horticultural crops. To investigate the impact of CO2 and temperature at elevated levels on tomato production and quality of fruits an experiment was conducted by growing plants in open top chambers. The tomato plants were raised at EC550 (elevated CO2 at 550 ppm) and EC700 (elevated CO2 at 700 ppm) alone and in combination with elevated temperature (ET) + 2 °C in the open top chambers. These elevate CO2 and temperature treatment effects were compared with plants grown under ambient conditions. Outcome of the experiment indicated that growth parameters namely plant stature in terms of height (152.20 cm), leaf number (158.67), canopy spread (6127.70 cm2), leaf area (9110.68 cm2) and total dry matter (223.0 g/plant) were found to be high at EC700 compared to plants grown at ambient conditions in open field. The plants grown at EC700 also exhibited significantly higher number of flowers (273.80) and fruits (261.13), more fruit weight (90.46 g) and yield (5.09 kg plant-1) compared to plants grown at ambient conditions in open field. The percent increase in fruit yield due to EC varied from 18.37 (EC550) to 21.41 (EC700) percent respectively compared to open field and the ET by 2 °C has reduced the fruit yield by 20.01 percent. Quality traits like Total Soluble Solids (3.67 °Brix), reducing sugars (2.48%), total sugars (4.41%) and ascorbic acid (18.18 mg/100 g) were found maximum in EC700 treated tomato than other elevated conditions. Keeping quality was also improved in tomato cultivated under EC700 (25.60 days) than the open field (17.80 days). These findings reveal that CO2 at 700 ppm would be a better option to improve both quantitative as well as qualitative traits in tomato. Among the combinations, EC550 + 2 °C proved better than EC700 + 2 °C with respect to yield as well as for the quality traits. The tomato grown under ET (+2 °C) alone recorded lowest growth and yield attributes compared to open field conditions and rest of the treatments. The positive influence of EC700 is negated to an extent of 14.35 % when the EC700 combined with elevated temperature of + 2 °C. The present study clearly demonstrates that the climate change in terms of increased temperature and CO2 will have a positive effect on tomato by way of increase in production and quality of fruits. Meanwhile the increase in EC beyond 700 ppm along with ET may reduce the positive effects on yield and quality of tomato.