Dynamic Optimization of Watering in Satsuma Mandarin using Neural Networks and Genetic Algorithms

In this study, an optimal watering scheduling that improves the quality of Satsuma mandarin grown in the field was investigated using an intelligent control technique combined with neural networks and genetic algorithms. The monthly data on fruit responses and climate factors were collected from August to November over 1996-2004. Dynamic changes in the sugar and citric acid contents of Satsuma mandarin, as affected by rainfall and sunshine duration, was first identified using neural networks, and then an optimal watering scheduling (rainfall management) that maximizes the sugar content and that minimizes the citric acid of Satsuma mandarin was determined through simulation of the identified neural-network model using genetic algorithms. The optimal value obtained was a combination of the marked increase in watering during the fruit-developmental stage (August and September) and a significant decrease in watering during the fruit-maturing stage (October and November) . From model simulation, a marked increase in watering during the former stage induced a lower citric acid content, and a significant decrease in watering during the latter stage induced an increase in sugar content. Drip irrigation is commonly used for increasing watering whereas plastic-film mulching is used for reducing it.

[1]  E. Baldwin,et al.  Sugars and Acids Influence Flavor Properties of Mango (Mangifera indica) , 2001 .

[2]  Y. Hashimoto,et al.  Sugar Accumulation Enhanced by Osmoregulation in Satsuma Mandarin Fruit , 1996 .

[3]  M. Génard,et al.  Leaf:fruit ratio and irrigation supply affect seasonal changes in minerals, organic acids and sugars of mango fruit , 2005 .

[4]  John H. Loughrin,et al.  Light Reflected from Red Mulch to Ripening Strawberries Affects Aroma, Sugar and Organic Acid Concentrations¶ , 2001, Photochemistry and photobiology.

[5]  T. Morimoto.  Dynamic Optimizations of Cultivation and Fruit-Storage Processes Using a Speaking Plant-based Intelligent Control Technique , 2003 .

[6]  E. Johansson,et al.  Groundcover materials improve quality and storability of 'Aroma' apples , 2005 .

[7]  D. Kumar,et al.  Irrigation planning using Genetic Algorithms , 2004 .

[8]  Geoffrey E. Hinton,et al.  How neural networks learn from experience. , 1992, Scientific American.

[9]  Y. Hashimoto.  RECENT STRATEGIES OF OPTIMAL GROWTH REGULATION BY THE SPEAKING PLANT CONCEPT , 1989 .

[10]  Robin Wardlaw,et al.  Application of genetic algorithms for irrigation water scheduling , 2004 .

[11]  S. Sykes,et al.  Effect of Salt and Water Stress on Fruit Quality, Physiological Responses, Macro- and Micro-Element Contents in Leaves of Satsuma Mandarin Trees under Greenhouse Conditions , 2001 .

[12]  H.-J. Tantau,et al.  Optimal control for plant production in greenhouses , 1991 .

[13]  Y. Ouchi,et al.  A Neural-Network Model for Predicting the Quality of 'Satsuma' Mandarin , 2005 .

[14]  Stephen A. Billings,et al.  Non-linear system identification using neural networks , 1990 .

[15]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[16]  Wahyu Purwanto,et al.  Simulative Estimation for the Identification of the Cumulative Response of a Plant Using Neural Networks. , 1996 .

[17]  H. Yakushiji,et al.  Sugar accumulation and partitioning in Satsuma mandarin tree tissues and fruit in response to drought stress , 1998 .

[18]  E. Stefanoudaki,et al.  WATER USE, GROWTH, YIELD AND FRUIT QUALITY OF 'BONANZA' ORANGES UNDER DIFFERENT SOIL WATER REGIMES , 1999 .

[19]  T. Morimoto,et al.  DYNAMIC OPTIMIZATION USING NEURAL NETWORKS AND GENETIC ALGORITHMS FOR TOMATO COOL STORAGE TO MINIMIZE WATER LOSS , 2003 .

[20]  I. Wu,et al.  SW—Soil and Water: Optimal Scheduling of a Micro-irrigation System under Deficit Irrigation , 2001 .

[21]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[22]  David E. Goldberg,et al.  Control system optimization using genetic algorithms , 1992 .

[23]  Geoffrey E. Hinton,et al.  Learning representations by back-propagation errors, nature , 1986 .

[24]  Tetsuo Morimoto,et al.  Optimization of heat treatment for fruit during storage using neural networks and genetic algorithms , 1997 .

[25]  Wendy D. Graham,et al.  Best Nitrogen and Irrigation Management Practices for Citrus Production in Sandy Soils , 2003 .

[26]  Jumah Amayreh,et al.  Developing crop coefficients for field-grown tomato (Lycopersicon esculentum Mill.) under drip irrigation with black plastic mulch , 2005 .

[27]  Steven R. Evett,et al.  Effect of mulch, irrigation, and soil type on water use and yield of maize , 1999 .

[28]  H. Challa,et al.  Optimal diurnal climate control in greenhouses as related to greenhouse management and crop requirements. , 1993 .

[29]  Tetsuo Morimoto,et al.  Intelligent Control for Plant Production System , 1995 .

[30]  Tetsuo Morimoto,et al.  Optimal control of physiological processes of plants in a green plant factory , 1995 .

[31]  Mark Mulligan,et al.  Optimal irrigation efficiency for maximum plant productivity and minimum water loss , 1999 .

[32]  Miguel A. Mariño,et al.  Use of Genetic Algorithm in Optimization of Irrigation Pumping Stations , 2004 .

[33]  R. W. McClendon,et al.  Optimal Control and Neural Networks Applied to Peanut Irrigation Management , 1996 .

[34]  Ali Fares,et al.  Evaluation of capacitance probes for optimal irrigation of citrus through soil moisture monitoring in an entisol profile , 2000, Irrigation Science.

[35]  K. Zushi,et al.  Effect of Soil Water Deficit on Vitamin C, Sugar, Organic Acid, Amino Acid and Carotene Contents of Large-fruited Tomatoes , 1998 .