Neural network modelling to predict weekly yields of sweet peppers in a commercial greenhouse

Abstract

Lin, W. C. and Hill, B. D. 2008. Neural network modelling to predict weekly yields of sweet peppers in a commercial greenhouse. Can. J. Plant Sci. 88: 531Á536. The production of greenhouse-grown sweet pepper (Capsicum annuum L.) is irregular with a peak-and-valley pattern of weekly yields. We monitored the yields and environment in a commercial greenhouse in British Columbia over six (2000Á2005) growing seasons. Light was defined as cumulative light over the current week, with L_1, L_2, L_3, L_4, L_5 and L_6 representing light over previous weeks. Temperature (AvgT) was defined as the current weekly average of 24-h air temperatures, with T_1, T_2 and T_3 representing temperatures over previous weeks. Inputs were also created for the current weekly yield (Y) and previous weekly yields (Y_1, Y_2, Y_3 and Y_4). Neural network (NN) modelling with up to 21 inputs was used to predict yields 1 wk (Y'1) and 2 wk (Y'2) in advance of the actual fruit harvest. Data for five different years were combined for model training with the year to be predicted held separate as a validation set. The best models used 13 inputs to predict Y'1 with an average R 2 of 0.66 over the 6 yr. Y_4, Y-Y_1, Y_1, L_1, Y, Y_3, Y-Y_3 and wk (of the year) were important inputs. The environmental inputs were of lesser importance, which suggests that the cyclic nature of pepper yields is inherent in the pepper biology. Predicting Y'2 was more difficult with an average R 2 of 0.59 over the 6 yr. NN have good potential for predicting pepper yields.Key words: Capsicum annuum L., flushing, fruit, greenhouse production, neural networks Lin, W. C. et Hill, B. D. 2008. Pre´vision du rendement du poivron dans une serre commerciale par mode´lisation sur re´seau neuronal. Can. J. Plant Sci. 88: 531Á536. La culture du poivron (Capsicum annuum L.) en serre donne des re´sultats irre´guliers avec un rendement hebdomadaire en dents de scie. Les auteurs ont e´tudie´le rendement et l'environnement de cette culture dans une serre commerciale de la Colombie-Britannique durant six saisons ve´ge´tatives (de 2000 a`2005). Pour la lumie`re, les auteurs ont utilise´la luminosite´cumulative de la semaine courante, L_1, L_2, L_3, L_4, L_5 et L_6 correspondant a`cette valeur pour les semaines ante´rieures. La tempe´rature (AvgT) e´tait e´gale a`la moyenne de la tempe´rature ambiante pendant 24 h pour la semaine en cours, T_1, T_2 et T_3 correspondant a`cette valeur pour les semaines ante´rieures. Les auteurs ont aussi cre´e´des intrants pour le rendement de la semaine courante (Y) et de la semaine ante´rieure (Y_1, Y_2, Y_3 et Y_4). La mode´lisation sur re´seau neuronal avec un maximum de 21 parame`tres permet de pre´voir le rendement des poivrons une semaine (Y'1) et deux semaines (Y'2) avant la re´colte proprement dite. Les auteurs ont combine´les donne´es de cinq anne´es pour former le mode`le, l'anne´e pour lesquelles les pre´visions devaient eˆtre calcule´es servant a`la validation. Les meilleurs re´sultats sont obtenus avec 13 parame`tres et le mode`le a pre´vu Y'1 avec ...

An Environmental Model Predicting Bacterial Ring Rot Symptom Expression

“…Agricultural systems usually involve many variables including weather that makes NN models particularly applicable for predicting agricultural outcomes. We have previously used NN modeling to predict maturity of spring wheat in western Canada (Hill et al 2002), cuticle cracking in greenhouse peppers and tomatoes (Ehret et al 2008), harvest dates of greenhouse-grown sweet peppers (Lin and Hill 2007), and the weekly yields of sweet peppers grown in commercial greenhouses (Lin and Hill 2008). The objective of this study was to determine if NN modeling could identify environmental factors influencing BRR symptoms to advance our understanding of Cms pathogen-hostenvironment interactions, predict disease severity, and improve early detection of the pathogen.…”

An Artificial Neural Network Model to Predict Wheat Stem Sawfly Cutting in Solid-Stemmed Wheat Cultivars

“…Agricultural systems usually involve many variables, including weather, which makes ANN models particularly applicable for predicting agricultural outcomes. ANN modeling has previously been used to predict beef carcass tenderness (Hill et al 2000), maturity and seeding date of spring wheat in western Canada (Major et al 1996;Hill et al 2002), harvest dates and quality of greenhouse peppers and tomatoes (Lin and Hill 2007;Ehret et al 2008;Lin and Hill 2008), and bacterial ring rot symptom expression in potatoes (Hill et al 2011). Therefore, the objective of this study was to use ANN modeling to predict the in-season tolerance level of solid-stemmed wheat cultivars to WSS, expressed as "% stems cut by the sawfly".…”

Artificial Neural Network Modeling of Greenhouse Tomato Yield and Aerial Dry Matter

“…ANNs allow us to develop models based on the intrinsic relations among the variables, without prior knowledge of their functional relationships [9]. Soft computing for ANN techniques has been widely used to develop models to predict different crop indicators, such as growth, yield, and other biophysical processes, and also because of the commercial importance of tomato [10][11][12][13][14][15][16][17][18][19][20][21][22][23] and other vegetables, such as lettuce [24][25][26][27][28][29][30], pepper [31][32][33][34], cucumber [35][36][37][38], wheat [39][40][41][42][43][44][45], rice [46][47][48], oat [49], maize [50,51], corn [52][53][54], corn and soybean [55], soybean…”