• Rural Digital Europe
• Publications close
• BJ close
• Computers and Electronics in Agricu... close

Abstract Efficient selection of drought-tolerant crops requires identification and high-throughput phenotyping (HTP) of the complex functional (especially canopy-conductance) traits that elicit plant responses to continually fluctuating environmental conditions. However, phenotyping of such dynamic physiology-based traits has been immensely challenging especially due to the limited availability of adequate methods that can provide continuous measurements of plant-water relations. Therefore, gravimetric phenotyping of plants is being increasingly used to allow one-to-one monitoring of plant-water relations and generate continuous evapotranspiration (ET) profiles. The gravimetric sensors or load cells can provide ET estimates at very high frequencies, e.g. 15-min interval, as chosen by the user. There is however, no study on understanding the optimum frequency or the sampling time at which ET needs to be monitored, such that data-redundancy, noise and processing overhead could be reduced. Hence, this paper makes a novel attempt in identifying the optimum sampling time for phenotyping ET from load cells time series. The proposed procedure includes an ensemble Machine-Learning (ML) approach for optimizing the sampling time through time series forecasting of ET profiles and classification of genotypes using the forecasted ET values. High-frequency load cells data from the LeasyScan, HTP platform, ICRISAT were used to derive the ET profiles at frequencies or scales varying from 15-min to 180-min, followed by ET forecasting and classification at each frequency. For both forecasting and classification, an ensemble of three ML algorithms i.e. Support Vector Machines (SVM), Artificial Neural Network (ANN) and Random Forests (RF) were leveraged. Consequently, the performance metrics (of both the operations) obtained from the ensemble were used to compute the entropy-based optimum sampling time. The results reveal that 60-min interval HTP data could be credibly used for both, forecasting ET as well as correctly classifying the genotypes.

Nutrient Manager for Rice (NMR) was tested in the Senegal River valley for the three seasons.NMR is a cloud-based decision-support tool for field-specific fertilizer recommendations.NMR increased rice yield by 1-2.3t/ha compared to farmers' fertilizer practice (FFP).NMR increased profitability by US$ 216-640 per ha compared to FFP. We evaluated recommendations provided by a cloud-based decision-support tool named Nutrient Manager for Rice (NMR) in terms of yield of irrigated lowland rice and profitability in comparison with farmers' fertilizer management practices (FFP) in the Senegal River valley. A total of 102 on-farm trials were conducted over the three seasons (2011 wet season, and 2012 and 2013 dry seasons). On average in each season, NMR recommendations increased rice yield by 1-2.3t/ha and profitability by US$ 216-640 per ha compared to FFP. Differences between FFP and NMR performance were mainly related to timing of the top-dressing of N fertilizer (delayed in the case of FFP), the number of N fertilizer applications (generally just one top-dressing for FFP; two or three for NMR), and application of K. We conclude that NMR offers a promising avenue for increasing the productivity and profitability of irrigated lowland rice in the Senegal River valley.