Introduction Directory UMM :Data Elmu:jurnal:A:Aquaculture:Vol187.Issue1-2.Jul2000:

prediction in the PNN model are difficult to interpret, suggesting besides prediction accuracy, model interpretation is an important issue for further investigation. q 2000 Elsevier Science B.V. All rights reserved. Keywords: Shrimp disease; Artificial neural networks; Logistic regression

1. Introduction

The global shrimp farming industry had a phenomenal growth in the 1980s mainly Ž . due to technological breakthroughs such as in hatchery practices and feed formulation , high profitability, and public support. Farmed shrimp amounted to about 660,200 mt in 1997, which accounted for about 22 of total shrimp production from both wild-caught and farm-raised sources. Asia produced about 70 of farmed shrimp and Western countries 30. Thailand was the leading producer followed by Ecuador, Indonesia, China, India, Bangladesh, Vietnam, Taiwan, and the Philippines in 1997. Black tiger Ž . shrimp Penaeus monodon was the most important species farmed in the Eastern Ž . Hemisphere while the western white shrimp Penaeus Õannamei dominated the West- Ž . ern Hemisphere Rosenbery, 1997 . Diseases have emerged as a major constraint to the sustainable growth of the shrimp aquaculture industry. Serious outbreaks of shrimp diseases have been reported in most of the major producing countries. Viral diseases have reduced shrimp production and have slowed the growth of the industry since 1991. Many diseases are linked to environmen- tal deterioration and stress associated with farm intensification. High profits in shrimp farming and increasing coastal land prices pushed shrimp farmers towards more intensive operation, first in Taiwan followed then by Thailand and other countries. Without effective control, intensive operations usually increase the nutrient and organic matter load to the ecosystem well beyond the carrying capacity of the environment. This often results in self-pollution that leads to more frequent disease outbreaks followed by crop failure. The collapse of the shrimp culture industry in Taiwan in 1988 and China in 1993 are apparent examples. Solution to the disease problems involves both prevention and cure. However, since treatment options for many shrimp diseases are either non-existent or ineffective, current emphasis is on prevention. Thus, the solution to the problem must deal with site selection, design, and sustainable farm management. The economics of alternate disease Ž control methods applying drugs and vaccines, fallowing the ponds after each harvest, . etc. need to be assessed and compared for sustainable development. In the long run, genetic improvement of the cultured species is likely to result in disease-resistant strains, greater tolerance to environmental variation, and faster growth. Improved virus-free fry may also reduce the disease problems in the grow-out stage. In response to the serious disease problems faced by the shrimp industry in Asia, a Ž . regional study was initiated in 1994 by Asian Development Bank ADB and Network Ž . of Aquaculture Centres in Asia-Pacific NACA aimed at providing a clearer under- standing on environmental problems and their economic impacts through a farm-level survey. The 1994 study was a result of a recommendation by a previous ADB–NACA regional study in 1990 which concluded that the diseases of aquatic animals and plants are closely linked to the environment and that environmental issues, including fish disease control, must be considered in the broader context of fish farming systems, design, site selection and management. The specific objective of the 1994 study was to assist governments in assessing policy options and formulating policies designed to improve the sustainability of the aquaculture industry. A detailed survey of almost 11,000 shrimp and carp farms was undertaken covering 16 countries and territories in the region. The shrimp survey extended to 2898 extensive, 1022 semi-intensive and 870 intensive shrimp farms. The survey results show that shrimp disease contributed to significant regional losses. A conservative US332.2 million per year was estimated as the total loss attributed to shrimp diseases: US143.3 million to intensive farms, US111.8 million to semi-inten- sive farms, and US77.1 million to extensive farms. The countries involved in the survey all suffered in various degrees from disease problems. For example, the propor- Ž . tion of intensive farms affected by disease defined as more than 20 stock losses was high in most countries, ranging from 12 in Malaysia to 100 in China. Semi-intensive and extensive farms were also reporting significant losses due to disease problems Ž . ADB–NACA, 1998 . The survey results also indicate that virtually all countries reported ‘unknown’ as the cause of the shrimp disease problems. As the causes of shrimp disease are poorly understood, research and improved extension activities are needed in properly identify- ing shrimp disease problems, and their prevention and cure. In this paper, we attempt to predict the occurrence of shrimp diseases based on farm site selection, design, and farm management practices. Prior research on disease prediction has essentially depended upon traditional statistical models with varying degrees of prediction accuracy. Further- more, the application of these models in sustainable aquaculture development and in controlling environmental deterioration has been very limited. In an attempt to look for a Ž . more reliable model, we developed a probabilistic neural network PNN to predict shrimp disease outbreaks in Vietnam using the ADB–NACA farm-level data from 480 Vietnamese shrimp farms. We also compared predictive performance of the PNN against the more traditional logistic regression approach on the same data set.

2. Methods and data