Time filter

Source Type

El Massi I.,University Ibn Zohr | Es-Saady Y.,University Ibn Zohr | El Yassa M.,University Ibn Zohr | Mammass D.,University Ibn Zohr | Benazoun A.,Agronomic and Veterinary Hassan II Institute
Proceedings - Computer Graphics, Imaging and Visualization: New Techniques and Trends, CGiV 2016 | Year: 2016

This study presents a multiple classifier system for automatic recognition of the damages and symptoms on plant leaves from images. The proposed approach is based on parallel combination of two kinds of classifiers, one is a neural network classifier that uses texture, color and shape features to distinguish between the damages and symptoms, then the other is a support vector machine (SVM) classifier that uses texture and shape features. In order to design our system, we have based on some existing approaches in the field that adopt a single classifier. The tests of this study were carried out on six classes including the damages of three pest insects (Leaf miners, Thrips and Tuta absoluta) and symptoms of three fungal diseases (Early blight, Late blight and Powdery mildew). The experimental results show the efficiency of our approach compared to the pervious approaches based on single classifier. The proposed approach is more effective and has the highest rate of recognition. © 2016 IEEE. Source

Massi I.E.,University Ibn Zohr | Saady Y.E.,University Ibn Zohr | Yassa M.E.,University Ibn Zohr | Mammass D.,University Ibn Zohr | Benazoun A.,Agronomic and Veterinary Hassan II Institute
Proceedings of 2015 IEEE World Conference on Complex Systems, WCCS 2015 | Year: 2015

The proposed approach aims at designing an automatic recognition system of the damages and symptoms on plant leaves. It is based on serial combination of two neural networks classifiers. The first classifier uses the color to differentiate between classes. Indeed, at this phase, the damages and/or the symptoms that have a similar or a nearest color are considered to belong to the same class. Then, the second classifier is used to differentiate between classes with similar color according to the shape and texture features. The approach is tested on four classes, including the damages of two kinds of pest insects (Leaf miners and the caterpillar Tuta absoluta), and the symptoms of two fungal diseases (Downy mildew and internal Powdery mildew). The experimental results indicate that the proposed approach would be interesting to use as means of diagnosis and phytosanitary problem recognition from images of damages and symptoms. © 2015 IEEE. Source

Hirich A.,Agronomic and Veterinary Hassan II Institute | Choukr-Allah R.,Agronomic and Veterinary Hassan II Institute | Ragab R.,UK Center for Ecology and Hydrology | Jacobsen S.-E.,Copenhagen University | And 2 more authors.
Journal of Materials and Environmental Science | Year: 2012

The objective of this study was to calibrate and validate the SALTMED model using field data of three growing seasons of quinoa (Chenopodium quinoa Willd.), chickpeas (Cicer arietinum) and sweet corn (Zea mays Saccharata) which were grown in the south of Morocco and subjected to six treatments of deficit irrigation with treated wastewater. The calibration focussed primarily on soil moisture related to quinoa in the field, measured yield and dry matter. The validation process of biomass production was based on use of the calibrated photosynthesis efficiency value of the control treatment. Plant parameters such as plant height and rooting depth, duration of each growth stage, sowing date, harvesting date, harvest index and leaf area index were based on field measurements and records. Crop coefficients Kc, Kcb, Fc were based on FAO56 paper. Soil parameters such as water retention curves were based on laboratory measurements. Initial soil water content and salinity were based on measurements either in the laboratory or in the field. Fine tuning of some crop and soil parameters was carried out in order to obtain a good calibration. Following successful calibration and validation, the SALTMED model proved its ability to predict soil moisture, yield and total dry matter for three growing seasons under several deficit irrigation strategies using treated wastewater. The model showed a very good agreement between the observed and simulated data, as well as being able to reveal the same difference between deficit irrigation strategies in terms of measured yield and total dry matter. Source

Yaakoubi A.,Moulay Ismai University | Chahlaoui A.,Moulay Ismai University | Rahmani M.,Agronomic and Veterinary Hassan II Institute | Elyachioui M.,Universite Ibn Tofail | Nejdi I.,Agronomic and Veterinary Hassan II Institute
Desalination and Water Treatment | Year: 2010

Olive mill wastewater (OMW) is the liquid by-product obtained from olive processing to extract virgin olive oil. Due to its acidic pH and high amounts in organic matter and phenols, OMW is very difficult to further purify. A solution would be to spread it on the soil. Hence, the objective of this study was to explore the effects of different OMW amounts on chemical characteristics of the soil cultivated with vineyard (cv. Italia), at different depths (10-30 cm and 30-60 cm). Our results show that after 2 months of spreading follow up, during 2 consecutive years (2005/2006 and 2006/2007), the upper soil layer (10-30 cm) of land plots irrigated by OMW became fertile; with an average ratio N.P.K of respectively, 1.54; 1.95 and 2. This study also showed the absence of risk of soil filling by the suspended matter and the residual oil brought by OMW. In the same way, the pH and the electric conductivity (EC) of the soil remain practically unchanged. The concentra-tion of OMW in calcium as well as the high content of soil limestone favoured the precipitation of limestone (CaCO3), especially in the upper soil layer (10-30 cm). An increase in soil organic matter and phenols, due to spreading with OMW, was found as estimated by direct cell counting. © 2010 Desalination Publications. Source

Affi N.,Agronomic and Veterinary Hassan II Institute | El-Fadl A.,Agronomic and Veterinary Hassan II Institute | El-Otmani M.,Agronomic and Veterinary Hassan II Institute | Benismail M.C.,Agronomic and Veterinary Hassan II Institute | El Mastor A.,Agronomic and Veterinary Hassan II Institute
Acta Horticulturae | Year: 2014

Water scarcity is becoming a major problem for agricultural development in the Mediterranean area. The Moroccan Massa region is a major supplier of tomato (Lycopersicum esculentum L.) both for export and for the domestic market. Current average water use for the tomato is 8,000 m3/ha for an 8-9 month production cycle. This research aims to develop irrigation strategies with this goal water saving with no effect on yield or fruit characteristics. The objective of the work was to assess the effects of the partial root zone drying irrigation (PRD) on leaf stomatal conductance, relative leaf water content (RWC), stem maximum daily shrinkage (MDS), root development and water use efficiency (WUE) of tomato grown in a greenhouse on a sandy substrate. Three treatments were applied: a control that received 100% of the water requirement, PRD-70 and PRD-50 in which 70% and 50% of water requirements were applied. The root system was divided in two sides with alternation of irrigation every three days. When vapor pressure deficit rises, PRD treatments showed a decrease in leaf stomatal conductance with, respectively, 17% and 26% compared to control. PRD-50 had the highest leaf water content during the experimental period. During periods of low and moderate climatic demand, MDS of all treatments showed the same trend. Whereas when vapor pressure deficit rose, PRD-50 had lower signal intensity. Compared to the control, number of root hairs increased by 120% and 190% in PRD-70 and PRD-50, respectively. Water use efficiency (WUE) was the highest (P < 0.001) for PRD-50 with 43 kg of fresh fruit per m3 of applied water. Source

Discover hidden collaborations