Adaptive Fertigation System Using Hybrid Vision-Based Lettuce Phenotyping and Fuzzy Logic Valve Controller Towards Sustainable Aquaponics

Sustainability is a major challenge in any plant factory, particularly those involving precision agriculture. In this study, an adaptive fertigation system in a three-tier nutrient film technique aquaponic system was developed using a non-destructive vision-based lettuce phenotype (VIPHLET) model integrated with an 18-rule Mamdani fuzzy inference system for nutrient valve control. Four lettuce phenes, that is, fresh weight, chlorophylls a and b, and vitamin C concentrations as outputted by the genetic programming-based VIPHLET model were optimized for each growth stage by injecting NPK nutrients into the mixing tank, as determined based on leaf canopy signatures. This novel adaptive fertigation system resulted in higher nutrient use efficiency (99.678%) and lower chemical waste emission (14.108 mg L-1) than that by manual fertigation (92.468%, 178.88 mg L-1). Overall, it can improve agricultural malpractices in relation to sustainable agriculture.

[1]  Salinda Buyamin,et al.  Enhanced Fertigation Control System towards Higher Water Saving Irrigation , 2018, Indonesian Journal of Electrical Engineering and Computer Science.

[2]  V. Cantore,et al.  Impact of irrigation regime and nitrogen rate on yield, quality and water use efficiency of wild rocket under greenhouse conditions , 2018 .

[3]  Steven R. Raine,et al.  Applied machine vision of plants – a review with implications for field deployment in automated farming operations 1 , 2010 .

[4]  Rodney B. Thompson,et al.  Decision support systems and models for aiding irrigation and nutrient management of vegetable crops , 2020 .

[5]  Nicola Ivan Giannoccaro,et al.  Development of Sensors-Based Agri-Food Traceability System Remotely Managed by a Software Platform for Optimized Farm Management , 2020, Sensors.

[6]  Elmer P. Dadios,et al.  Genetic algorithm with adaptive and dynamic penalty functions for the selection of cleaner production measures: a constrained optimization problem , 2006 .

[7]  M. L. Segura,et al.  Integral Management of Irrigation Water in Intensive Horticultural Systems of Almería , 2017 .

[8]  F. Di Gioia,et al.  A decision support system (GesCoN) for managing fertigation in vegetable crops. Part II—model calibration and validation under different environmental growing conditions on field grown tomato , 2015, Front. Plant Sci..

[9]  Rogelio Ruzcko Tobias,et al.  Lettuce growth stage identification based on phytomorphological variations using coupled color superpixels and multifold watershed transformation , 2020 .

[10]  A. Cardoso,et al.  DOSES DE FÓSFORO NA FERTIRRIGAÇÃO DE MUDAS EM SUBSTRATO A BASE DE FIBRA DE COCO E INFLUÊNCIA NA PRODUÇÃO DO REPOLHO , 2017 .

[11]  Rogelio Ruzcko Tobias,et al.  Lettuce life stage classification from texture attributes using machine learning estimators and feature selection processes , 2020 .

[12]  Daniela de Carvalho Lopes,et al.  Development and evaluation of an automated system for fertigation control in soilless tomato production , 2014 .

[13]  Hani Sewilam,et al.  Efficient utilization of aquaculture effluents to maximize plant growth, yield, and essential oils composition of Origanum majorana cultivation , 2021, Annals of Agricultural Sciences.

[14]  Taru Palosuo,et al.  Towards improved calibration of crop models – Where are we now and where should we go? , 2018 .