Application note: SIMCE: An expert system for seedling weed identification in cereals

Identification of weed seedlings is a difficult task. An expert system to help farmers and extension workers to identify weed species in cereals has been developed. The expert system uses a hierarchical classification and a mix of the text description, photographs and artistic pictures. The system is supported by a data base containing information about 41 weed species and 128 colour images. The expert system was evaluated following the conventional expert system evaluation methodologies. Results of the validation indicated that non-expert users were able to make identification using the expert system. A total of 149 identifications were performed and 63% were identified correctly. The erroneous identifications tended to cluster around monocot species; especially Avena sterilis, Lolium rigidum, Phalaris ssp. and Bromus sterilis were misidentified. Results of the validation process and the writing suggestions provided by the participants were used to implement improvements in the system. The program can be used as an identification tool for farmers and technicians and for educational purposes.

[1]  G. M. Pasqual,et al.  Development of an expert system for the identification and control of weeds in wheat, triticale, barley and oat crops☆ , 1994 .

[2]  Alberto Fereres,et al.  Cereal aphids expert system (CAES): Identification and decision making , 1993 .

[3]  A. Carlisle Scott,et al.  Practical guide to knowledge acquisition , 1991 .

[4]  Jon Sticklen,et al.  NEPER-Weed: A Picture-Based Expert System for Weed Identification , 1996 .

[5]  Gary S. Kahn,et al.  The Mud System , 1986, IEEE Expert.

[6]  Luis García-Torres,et al.  SEMAGI — an expert system for weed control decision making in sunflowers , 1995 .

[7]  B. Chandrasekaran,et al.  Generic Tasks in Knowledge-Based Reasoning: High-Level Building Blocks for Expert System Design , 1986, IEEE Expert.

[8]  J. Dorado,et al.  Weed seedbank response to crop rotation and tillage in semiarid agroecosystems , 1999, Weed Science.

[9]  Gareth Edwards-Jones,et al.  Knowledge-based systems for pest management: an applications-based review† , 1992 .

[10]  José Luis González-Andújar,et al.  Development of a prototype expert system (SIEXMAL) for identification of weeds in cereals. , 1990 .

[11]  Jordi Recasens Guinjuan,et al.  Weed-one: sistema multimedia de enseñanza asistida por ordenador para el aprendizaje en el reconocimiento visual de plántulas de malas hierbas , 1995 .

[12]  Alexander B. Sideridis,et al.  A diagnostic expert system for honeybee pests , 2002 .

[13]  Narasipur S. Murali,et al.  Application of information technology in plant protection in Denmark: from vision to reality , 1999 .

[14]  José Luis González-Andújar,et al.  Spatial distribution of annual grass weed populations in winter cereals , 2003 .

[15]  J. Knight.  The role of decision support systems in integrated crop protection , 1997 .

[16]  Richard E. Plant,et al.  Knowledge Based Systems in Agriculture , 1991 .

[17]  G. Barralis,et al.  MALHERB, logiciel de reconnaissance des mauvaises herbes des cultures: approche botanique , 1991 .

[18]  Steve Harrison,et al.  Validation of agricultural expert systems , 1991 .

[19]  G. Ash,et al.  An expert system for the management of Botrytis cinerea in Australian vineyards. I. Development , 1998 .

[20]  Eduardo Mosqueira-Rey,et al.  Validation of intelligent systems: a critical study and a tool , 2000 .

[21]  José Luis González Andújar,et al.  Aplicación de los sistemas expertos en agricultura , 1996 .