An intelligent system for predicting Thrips tabaci Linde pest population dynamics allied to cotton crop

Abstract

The agricultural sector in India is up against a series of problems when it comes to increasing crop productivity. A number of successful researches have been carried out to discover productive agricultural practices to improve crop cultivation but despite their efforts, productivity achieved by most of the farmers has not been in upper-bound level. The prime reason stated globally for crop loss is Insect pests. An efficient pest management technique can be devised if we could predict in advance the occurrences of peak activities of a given pest. Researchers are undertaken to understand the pest population dynamics by employing analytical and other techniques on pest surveillance data sets. In this paper, we present an intelligent system for pest prediction in cotton crop with the aid of the data obtained from College of Agriculture, Raichur, India. We make an effort to understand population dynamics of Thrips tabaci Linde (Thrips) pest on cotton (Gossypium Arboreum) crop using neural networks by analyzing pest surveillance data. The Multi-layer perceptron neural network with back-propagation training algorithm is utilized in the design of the presented intelligent system. The results show that neural network system can be able to give results with a very high degree of accuracy and is best suited to build a prediction system. With the aid of this pest prediction system, the farming communities get more beneficiaries in crop productivity.

The occurrence of Scirtothrips dorsalis Hood in mango orchards and factors influencing its population dynamics in Taiwan

“…Previous studies have not adopted DT for S. dorsalis research. However, Patil et al (2009) employed ANNs for analyzing S. dorsalis data acquired from 2003 to 2008, showing that the correlation between the prediction results and the actual value was higher than 0.96. In our study, although the data were from a one-year period, we selected parts of the data as actual values for validation and demonstrated that the overall model derived from DT was superior to that derived from ANNs.…”

“…The data of this study did not allow us to discuss the influence of pesticides on S. dorsalis population. Patil et al (2009) reported that highly accurate prediction results can help farmers manage pests, prevent crop loss, and reduce pesticide usage, and simultaneously mitigates environmental pollution. Nonetheless, future studies could focus on optimizing the accuracy of the prediction model by incorporating other variables that may influence the occurrence of S. dorsalis such as absolute humidity, dew point, saturation deficit, and sunshine ratio as suggested by Chang (1997).…”

“…The quick classification and phylogeny of pests have also been investigated using data mining techniques (Kaila, 1999;Regier et al, 2012). Moreover, Patil et al (2009) applied artificial neural networks (ANNs) for predicting the population dynamics of onion thrips; their results exhibited high accuracy, indicating that ANNs is a suitable approach for analyzing pest prediction systems. Recently, data mining techniques have been used to study S. dorsalis (Mehle and Trdan, 2012;Wei et al, 2012) and can also be adopted to establish its preliminary prediction model (Wei et al, 2012).…”

“…Data mining techniques were applied to insect and other agricultural researches (Abdullah et al, 2003;Patil et al, 2009). Dynamic monitoring data for agriculture obtained from various governmental agencies and institutions were integrated and standardized; data on pest detection, pesticide application, and agrometeorological records were used for short-term forecasting and for solving pest management problems in Pakistan (Abdullah et al, 2003).…”