Modelling the impact of different irrigation regimes and mulching on strawberry crop growth and water use in the arsenic-contaminated Bengal basin.

Replacement of water-intensive winter rice with strawberry (Fragaria × ananassa Duch.) may restrict groundwater extraction and improve water productivity and sustainability of agricultural production in the arsenic-contaminated Bengal basin. The potential of strawberry cultivation in terms of yield obtained and water use efficiency need to be evaluated under predominant soil types with mulch applications. Water-driven model AquaCrop was used to predict the canopy cover, soil water storage and above-ground biomass of strawberry in an arsenic-contaminated area in the Bengal basin. After successful calibration and validation over three seasons, AquaCrop was used over a range of management scenarios (nine drip-irrigation × three soil types × four mulch materials) to identify the best irrigation options for a drip-irrigated strawberry crop. The most appropriate irrigation of 176 mm for clay loam soil in lowland and 189 mm for sandy clay loam in medium land rice areas and the use of organic mulch from locally available jute agrotextile improved 1.4 times higher yield and 1.7 times higher water productivity than that of without mulch. Strawberry can be introduced as an alternative crop replacing rice in non-traditional upland and medium land areas of the arsenic-contaminated Bengal basin with 88% lower groundwater extraction load and better economic return to farmers.

Machine Learning approach to Predict net radiation over crop surfaces from global solar radiation and canopy temperature data.

As the ground-based instruments for measuring net radiation are costly and need to be handled skillfully, the net radiation data at spatial and temporal scales over Indian subcontinent are scanty. Sometimes, it is necessary to use other meteorological parameters to estimate the value of net radiation, although the prediction may vary based on season, ground cover and estimation method. In this context, artificial intelligence can be used as a powerful tool for predicting the data considering past observed data. This paper proposes a novel method to predict the net radiation for five crop surfaces using global solar radiation and canopy temperature. This contribution includes the generation of real-time data for five crops grown in West Bengal state of India. After manual analysis and data preprocessing, data normalization has been done before applying machine learning approaches for training a robust model. We have presented the comparison in various machine learning algorithm such as ridge and spline regression, random forest, ensemble and deep neural networks. The result shows that the gradient boosting regression and ridge regression are outperforming other ML approaches. The estimated predictors enable to reduce the number of resources in terms of time, cost and manpower for proper net radiation estimation. Thus, the problem of predicting net radiation over various crop surfaces can be sorted out through ML algorithm.