Expert Systems To Support Environmental ... - ACS Publications

Chapter 5

Expert Systems To Support Environmental Sampling, Analysis, and Data Validation Downloaded by UNIV OF CALIFORNIA SANTA BARBARA on March 16, 2018 | https://pubs.acs.org Publication Date: July 5, 1990 | doi: 10.1021/bk-1990-0431.ch005

1

2

Ramon A. Olivero and David W. Bottrell 1

Environmental Programs Office, Lockheed Engineering and Sciences Company, 1050 East Flamingo Road, Las Vegas, NV 89119 Environmental Monitoring Systems Laboratory—Las Vegas, U.S. Environmental Protection Agency, P.O. Box 93748, Las Vegas, NV 89193-3478 Expert systems are being developed to address the decision-making needs for data generation activities (i.e., sampling, analysis, and data validation) at the U.S. Environmental Protection Agency. This paper describes the Environmental Sampling Expert System, the Smart Method Index, and Computer-Aided Data Review and Evaluation, among other systems under development at the Agency's Environmental Monitoring Systems Laboratory i n Las Vegas, Nevada, and discusses their design, operation, and impact on environmental investigations. Appropriate data quality i s fundamental to environmental decision making, monitoring, and remediation. Requirements for standardization and documentation and the need for rapid response from personnel with different levels of training make the application of expert system technology a promising approach for the Agency. Improvement i n quality and consistency of environmental data through the application of expert systems i n the government and private sectors i s expected to translate into lower costs, from both economic and social perspectives. 2

The U.S. Congress has t a s k e d t h e U.S. E n v i r o n m e n t a l P r o t e c t i o n Agency (EPA) w i t h d i r e c t i n g and o v e r s e e i n g t h e e f f o r t t o c o n t r o l and remediate p o l l u t i o n nationwide. The Superfund program was s p e c i f i c a l l y e s t a b l i s h e d t o a s s e s s and remediate e x i s t i n g hazardous waste s i t e s . Superfund t e c h n i c a l e v a l u a t i o n s h e l p s e t c l e a n u p p r i o r i t i e s f o r s i t e s a c c o r d i n g t o t h e r i s k posed t o human and ecological health. I n v e s t i g a t i o n s a t hazardous waste s i t e s i n v o l v e p l a n n i n g , management, d a t a c o l l e c t i o n , r i s k assessment, t e c h n o l o g y s e l e c t i o n , and e n g i n e e r i n g d e s i g n and c o n s t r u c t i o n on a v e r y l a r g e s c a l e . The d e c i s i o n - m a k i n g r e s p o n s i b i l i t i e s a r e numerous and v a r i e d . Often 0097-6156/90/0431-Ό069$06.00/0 © 1990 American Chemical Society

Hushon; Expert Systems for Environmental Applications ACS Symposium Series; American Chemical Society: Washington, DC, 1990.

Downloaded by UNIV OF CALIFORNIA SANTA BARBARA on March 16, 2018 | https://pubs.acs.org Publication Date: July 5, 1990 | doi: 10.1021/bk-1990-0431.ch005

70

EXPERT SYSTEMS FOR ENVIRONMENTAL APPLICATIONS

t h e y a r e beyond what can be e f f i c i e n t l y o r r e l i a b l y performed by the a v a i l a b l e p e r s o n n e l . T h i s may be due t o the b r e a d t h o f e x p e r i e n c e r e q u i r e d o r t o the amount o f a v a i l a b l e d a t a t h a t i s r e l e v a n t to a p a r t i c u l a r d e c i s i o n . Computers a r e b e i n g i n c r e a s i n g l y a p p l i e d by EPA t o h e l p e x p e d i t e the Agency's work. I n a d d i t i o n t o t a s k - a u t o m a t i o n computer programs, systems t h a t use a r t i f i c i a l i n t e l l i g e n c e t e c h n i q u e s are b e i n g d e v e l o p e d t o s e r v e as "smart" a d v i s o r s f o r d e c i s i o n makers a t many d i f f e r e n t l e v e l s . The EPA E n v i r o n m e n t a l M o n i t o r i n g Systems L a b o r a t o r y i n Las Vegas, Nevada, i s d e v e l o p i n g e x p e r t systems t o i n c r e a s e the a c c u r a c y , t i m e l i n e s s , and c o s t e f f e c t i v e n e s s o f f i e l d s a m p l i n g , c h e m i c a l a n a l y s i s , and a n a l y t i c a l d a t a v a l i d a t i o n w i t h i n the Superfund program. EPA D e c i s i o n - M a k i n g Needs D e c i s i o n s made by EPA s t a f f and c o n t r a c t o r s c o v e r a wide range, depending on the n a t u r e o f the problem and the s t a g e o f p r o j e c t a c t i v i t y . A p r e l i m i n a r y s t u d y u s i n g r i s k assessment t e c h n i q u e s may be concerned w i t h e s t a b l i s h i n g the e x i s t e n c e and e x t e n t o f an environmental hazard. T y p i c a l l y , the d a t a r e q u i r e m e n t s a r e the c o n c e n t r a t i o n s o f p o l l u t a n t s i n a s p e c i f i c environment ( e . g . , l e v e l s o f p e s t i c i d e s i n a s u b s u r f a c e water s o u r c e ) . A t more advanced s t a g e s , d e c i s i o n s must be made about the need f o r r e m e d i a l a c t i o n s o r p o l l u t a n t - g e n e r a t i o n c o n t r o l s and the s e l e c t i o n o f a p p r o p r i a t e technologies f o r implementation. The process i s monitored throughout to e s t a b l i s h p r o g r e s s , v e r i f y attainment o f o b j e c t i v e s , or assure continued compliance. A l l o f these d e c i s i o n s r e q u i r e q u a n t i t a t i v e and q u a l i t a t i v e i n f o r m a t i o n o f known q u a l i t y and a p p r o p r i a t e f o r the i n t e n d e d use. The e f f i c i e n t i n t e r p r e t a t i o n and a p p l i c a t i o n o f adequate d a t a i s the c o r n e r s t o n e f o r sound d e c i s i o n making i n a l l a r e a s o f the EPA m i s s i o n . EPA u t i l i z e s p e r s o n n e l from many a r e a s o f e x p e r t i s e . For example, a p a r t i c u l a r p r o j e c t may i n v o l v e p e o p l e w i t h backgrounds i n e n v i r o n m e n t a l e n g i n e e r i n g , h e a l t h and s a f e t y , c h e m i s t r y , e a r t h s c i e n c e s , s t a t i s t i c s , c o n s t r u c t i o n e n g i n e e r i n g , management, and law, among o t h e r s . Many o f the s p e c i f i c s k i l l s needed t o p l a n and e x e c u t e the v a r i e t y of a c t i v i t i e s i n v o l v e d i n environmental i n v e s t i g a t i o n s a r e l e a r n e d through e x p e r i e n c e and specialized t r a i n i n g , r a t h e r than through formal education. The body o f s p e c i a l i z e d knowledge d e v e l o p e d i n the r e c e n t p a s t by the e n v i r o n m e n t a l community i s n o t i n t e g r a t e d . Technologies develop f a s t e r t h a n documentation and, i n many c a s e s , the knowledge i s more e m p i r i c a l than t h e o r e t i c a l . Each member o f an e n v i r o n m e n t a l team has a v e r y s p e c i f i c mission. The s u c c e s s o f the p r o j e c t depends on the o v e r a l l c o o r d i n a t i o n o f the i n d i v i d u a l elements. Communication and c r o s s t r a i n i n g are c r i t i c a l f o r the e f f e c t i v e and e f f i c i e n t accomplishment o f the EPA m i s s i o n . U n f o r t u n a t e l y , the demand f o r t r a i n e d and e x p e r i e n c e d e n v i r o n m e n t a l p r o f e s s i o n a l s f a r outweighs the c u r r e n t availability. EPA has u n d e r t a k e n the development o f c o m p u t e r i z e d i n f o r m a t i o n systems, d e c i s i o n s u p p o r t systems, and "smart" a d v i s o r s t o p r o v i d e a c c e s s t o the s p e c i a l i z e d knowledge o f e x p e r t s and c o n f r o n t



5.

OLIVERO AND BOTTRELL

Sampling, Analysis, and Data Validation71

u n d e r s t a f f i n g and h i g h p e r s o n n e l t u r n o v e r r a t e . A d v i s o r y s o f t w a r e i s commonly termed " e x p e r t systems" o r "knowledge systems." To a c h i e v e a h i g h l e v e l o f performance f o r a p a r t i c u l a r t a s k , t h i s type of computer program i n c o r p o r a t e s the knowledge and s i m u l a t e s the d e c i s i o n - m a k i n g p r o c e s s e s o f human e x p e r t s . E x p e r t systems have the p o t e n t i a l for increasing the a c c u r a c y , timeliness, and consistency of decisions. Decision-making f o r e n v i r o n m e n t a l work r e q u i r e s combining i n f o r m a t i o n o b t a i n e d from e n v i r o n m e n t a l d a t a and s t a n d a r d p r o c e d u r e s w i t h judgement. I t s h o u l d be based on the b e s t d a t a and i n f o r m a t i o n a v a i l a b l e , f o l l o w e x i s t i n g EPA r e g u l a t i o n s , and be c a r r i e d out by s k i l l e d personnel. E x p e r t systems can guide the u s e r t o r e l e v a n t d a t a bases and r e g u l a t i o n s (and h e l p i n t h e i r i n t e r p r e t a t i o n and a p p l i c a t i o n ) , as w e l l as o f f e r s p e c i f i c a d v i c e b a s e d on the e x p e r i e n c e o f human e x p e r t s . A key a r e a f o r the a p p l i c a t i o n o f e x p e r t systems i s q u a l i t y assurance f o r d a t a t h a t a r e t o be used as i n p u t f o r d e c i s i o n making i n the v a r i o u s a s p e c t s o f e n v i r o n m e n t a l work. These systems not o n l y have a b e n e f i c i a l impact on the q u a l i t y , t i m e l i n e s s , and c o s t - e f f e c t i v e n e s s o f the d a t a - g e n e r a t i o n p r o c e s s i t s e l f , b u t a l s o have a p o s i t i v e e f f e c t on the d e c i s i o n making and a c t i o n phases o f p r o j e c t s . Environmental Data-Generation

Process

EPA has d e v e l o p e d a s t a n d a r d i z e d procedure f o r g e n e r a t i o n o f d a t a for environmental d e c i s i o n s . The d a t a q u a l i t y o b j e c t i v e (DQO) p r o c e d u r e e s t a b l i s h e s a sequence o f o r d e r e d s t e p s t o a s s u r e t h a t the d a t a g e n e r a t e d i s o f known q u a l i t y and a p p r o p r i a t e f o r the i n t e n d e d use (1) . S p e c i f i c DQO g u i d e l i n e s have been d e v e l o p e d f o r Superfundr e l a t e d work ( 2 ) . The o v e r a l l p r o c e s s o f g e n e r a t i n g e n v i r o n m e n t a l i n f o r m a t i o n i n v o l v e s f i e l d s a m p l i n g , c h e m i c a l a n a l y s i s o f the c o l l e c t e d samples, v a l i d a t i o n o f the d a t a c o l l e c t e d , and e v a l u a t i o n o f the q u a l i t y and u s e a b i l i t y o f the d a t a based on the p r e - e s t a b l i s h e d DQOs. DQOs i n c l u d e statements i n terms o f p r e c i s i o n , accuracy, d e t e c t a b i l i t y , r e p r e s e n t a t i v e n e s s , c o m p a r a b i l i t y , and completeness of the a n a l y t i c a l d a t a . These q u a n t i t a t i v e parameters a r e used t o s e l e c t a p p r o p r i a t e s a m p l i n g and a n a l y s i s t e c h n i q u e s . A f t e r sample c o l l e c t i o n and a n a l y s i s , d a t a q u a l i t y i s a s s e s s e d t o e s t a b l i s h the degree o f a t t a i n m e n t o f the DQOs. To c o n t r o l , m o n i t o r , and c o r r e c t the p r o c e s s , quality assurance and quality control (QA/QC) p r o c e d u r e s a r e implemented throughout. S c i e n t i s t s a t the Las Vegas l a b o r a t o r y a r e d e v e l o p i n g e x p e r t systems t o s u p p o r t v a r i o u s key a s p e c t s o f t h i s d a t a - g e n e r a t i o n process. The a s p e c t s c u r r e n t l y b e i n g a d d r e s s e d i n c l u d e s e l e c t i o n of s a m p l i n g t e c h n i q u e s , s e l e c t i o n o f c h e m i c a l a n a l y t i c a l methods, evaluation of analytical l a b o r a t o r y performance, and data validation. F i g u r e 1 d e p i c t s the phases o f the d a t a - g e n e r a t i o n p r o c e s s and systems b e i n g developed a t the Las Vegas l a b o r a t o r y t o address them. The EPA Q u a l i t y Assurance Management S t a f f i n Washington, D.C., i s d e v e l o p i n g an e x p e r t system t o a s s i s t i n e s t a b l i s h i n g DQOs.



Figure 1. Expert Systems Being Developed to Support the E P A Environmental Data Generation Process.


03

ο

ι

I

1

s

αϊ

1

5.




E n v i r o n m e n t a l Sampling E x p e r t System Sampling and a n a l y s i s c o n s t i t u t e the two major components o f the measurement phase. To a g r e a t e x t e n t , t h e i r combined i n d i v i d u a l e r r o r s determine the o v e r a l l measurement e r r o r . Development, improvement, and c h a r a c t e r i z a t i o n a c t i v i t i e s f o r c h e m i c a l a n a l y s i s t e c h n o l o g y have r e c e i v e d more a t t e n t i o n t h a n those f o r f i e l d sampling technology. S i g n i f i c a n t p r o g r e s s has been made i n l a b o r a t o r y and f i e l d a n a l y s i s t e c h n i q u e s , b u t s a m p l i n g remains d i f f i c u l t t o c o n t r o l , l a r g e l y due t o i t s c o m p l e x i t y and d i v e r s i t y . C o n s e q u e n t l y , the f i e l d s a m p l i n g s t e p has the p o t e n t i a l t o i n t r o d u c e unaccounted u n c e r t a i n t y i n the d a t a . The o b j e c t i v e o f the E n v i r o n m e n t a l Sampling E x p e r t System (ESES) i s t o c o n s o l i d a t e knowledge o f a l t e r n a t i v e t e c h n i q u e s i n o r d e r t o p l a n s a m p l i n g a c t i v i t i e s a t hazardous waste s i t e s i n an e f f i c i e n t , c o n s i s t e n t , and c o o r d i n a t e d f a s h i o n . The system i s b u i l t i n modules t h a t address v a r i o u s a s p e c t s o f sample c o l l e c t i o n . I n p u t i s based on p r o j e c t DQOs and s i t e c h a r a c t e r i s t i c s . The u s e r i s e x p e c t e d t o be f a m i l i a r w i t h the DQO p r o c e s s and p r o v i d e n e c e s s a r y background i n f o r m a t i o n on the s i t e . ESES makes e x t e n s i v e use o f h y p e r t e x t t e c h n i q u e s ( 3 ) . H y p e r t e x t i s a method t o p r e s e n t i n f o r m a t i o n i n a computer. Each p o r t i o n o f t e x t p r e s e n t e d on the computer s c r e e n may c o n t a i n h i g h l i g h t e d terms which can be s e l e c t e d f o r f u r t h e r e x p l a n a t i o n . The e x p l a n a t i o n w i l l appear i n a s e p a r a t e "window" on the s c r e e n and the u s e r can r e t u r n t o the o r i g i n a l t e x t when f i n i s h e d w i t h the window. Each e x p l a n a t i o n window may c o n t a i n more h y p e r t e x t terms, which can be s e l e c t e d a t the u s e r ' s command, forming a c h a i n of concepts. This f e a t u r e allows f o r v a r i o u s l e v e l s of o n - s c r e e n i n f o r m a t i o n a c c o r d i n g t o the u s e r ' s l e v e l o f background i n the s u b j e c t m a t t e r . N o v i c e u s e r s w i l l make e x t e n s i v e use o f h y p e r t e x t and find the system s e l f - e x p l a n a t o r y , w h i l e more e x p e r i e n c e d u s e r s w i l l not be f o r c e d t o r e a d f a m i l i a r i n f o r m a t i o n . The use o f h y p e r t e x t g i v e s ESES v a l u e as a t r a i n i n g t o o l and a l s o makes i t a p p r o p r i a t e f o r use by s t a f f members w i t h w i d e - r a n g i n g backgrounds and l e v e l s o f e x p e r t i s e . The ESES p r o t o t y p e was d e v e l o p e d w i t h the KnowledgePro V e r s i o n 1.4 "knowledge p r o c e s s i n g " s o f t w a r e package (Knowledge Garden, I n c . , Nassau, New Y o r k ) ( 4 ) . T h i s s o f t w a r e has b u i l t - i n f a c i l i t i e s f o r h y p e r t e x t and h y p e r g r a p h i c s m a n i p u l a t i o n , as w e l l as e x t e n s i v e s u p p o r t f o r u s e r i n t e r f a c e development. A backward-chaining i n f e r e n c e engine p e r m i t s the i m p l e m e n t a t i o n o f d e c i s i o n r u l e s . In KnowledgePro d a t a are k e p t i n l i s t s and s e v e r a l l i s t - m a n i p u l a t i o n p r o c e d u r e s , s i m i l a r t o LISP programming a r e p r o v i d e d . External l i n k s t o memory-resident P a s c a l code can a l s o be implemented. ESES t a k e s advantage o f t h i s u s e f u l f e a t u r e t o implement s t a t i s t i c a l r o u t i n e s . However, the i n t e r f a c e scheme i s n o t v e r y e f f i c i e n t , and thus f o r c e s the programmer t o l i m i t the use o f e x t e r n a l r o u t i n e s t o the most e s s e n t i a l t a s k s . The ESES e x p e r t system p r o v i d e s an e x p l a n a t i o n f a c i l i t y which j u s t i f i e s the recommendations g i v e n t o the u s e r ( t h i s i s the HOW f e a t u r e , a l s o f r e q u e n t l y r e f e r r e d t o as the WHY f e a t u r e i n e x p e r t system l i t e r a t u r e ) . A comprehensive r e p o r t o f the s e s s i o n can be p r i n t e d f o r f u t u r e r e f e r e n c e ; which i n c l u d e s the recommendations g i v e n , HOW e x p l a n a t i o n s , a p r o f i l e o f the problem d e s c r i b e d by the



74


user, and a copy o f t h e h y p e r t e x t e x p l a n a t i o n s requested. A d d i t i o n a l l y , s e s s i o n s c a n be saved t o resume c o n s u l t a t i o n a t a l a t e r time. As ESES h a s grown i n s i z e and c o m p l e x i t y , t h e IBM-PC p l a t f o r m and KnowledgePro 1.4 s o f t w a r e have become l e s s c a p a b l e o f adequate performance. To o b t a i n a c c e p t a b l e performance, t h e system must be used on an 80286 -based machine r u n n i n g a t l e a s t a t 12 MHz c l o c k speed. T h e r e f o r e , an 80386-based microcomputer i s a b e t t e r environment f o r t h i s system. EPA needs e x p e r t systems t h a t r u n on i t s e x t e n s i v e i n s t a l l e d base o f IBM-PC c o m p a t i b l e m i c r o c o m p u t e r s . T h i s requirement i s t h e major hardware c o n s t r a i n t f o r any system d e v e l o p e d f o r Agency-wide d i s t r i b u t i o n . Furthermore, enhancements such as extended memory; new, f a s t e r m i c r o p r o c e s s o r s ; massive s t o r a g e systems; and even s p e c i a l p o i n t i n g d e v i c e s a r e n o t a v a i l a b l e , a t t h i s time, throughout t h e Agency. G i v e n these hardware l i m i t a t i o n s , t h e system improvement e f f o r t has c o n c e n t r a t e d on t h e s o f t w a r e component. The use o f a f a s t e r development software product w i t h b e t t e r i n p u t and o u t p u t c a p a b i l i t i e s w i l l a l l o w f o r g r e a t e r m o d u l a r i z a t i o n and more s t o r a g e o f temporary i n f o r m a t i o n on d i s k , thus e a s i n g main memory usage and f a c i l i t a t i n g the i n t e r f a c i n g to external routines. This k i n d o f s o f t w a r e i s e x p e c t e d t o s i g n i f i c a n t l y i n c r e a s e performance. The n e x t g e n e r a t i o n o f KnowledgePro s o f t w a r e p r o m i s e s t o meet these r e q u i r e m e n t s and i s b e i n g c u r r e n t l y t e s t e d , i n i t s b e t a v e r s i o n , by the L a s Vegas l a b o r a t o r y . Two v e r s i o n s o f ESES a r e c u r r e n t l y under development, t h e s o i l m e t a l s a p p l i c a t i o n (ESES-SM) and the ground-water a p p l i c a t i o n (ESESGW) . Knowledge e n g i n e e r i n g f o r the system ( t h e p r o c e s s o f a c q u i r i n g and o r g a n i z i n g t h e knowledge and d e c i s i o n r u l e s ) i s done by i t e r a t i v e i n t e r v i e w i n g o f recognized experts i n the areas o f f i e l d s a m p l i n g , s o i l s c i e n c e , c h e m i s t r y , h y d r o g e o l o g y , s t a t i s t i c s , and q u a l i t y assurance. ESES-SM a s s i s t s i n d e s i g n i n g a s a m p l i n g p l a n f o r determining the extent o f metal p o l l u t i o n i n s o i l ( 5 ) . I t provides advice on a p p r o p r i a t e statistical designs, QA/QC p r o c e d u r e s , s a m p l i n g t e c h n i q u e s and t o o l s , sample h a n d l i n g , budget r e q u i r e m e n t s , p e r s o n n e l s a f e t y , and documentation. ESES-GW h a s an extended a n a l y t e coverage t h a t i n c l u d e s o r g a n i c contaminants i n a d d i t i o n t o m e t a l contaminants ( 6 ) . The c u r r e n t ESES-GW p r o t o t y p e h e l p s d e c i d e what types o f ground-water s a m p l i n g pumps and d e v i c e s a r e a p p r o p r i a t e t o use under g i v e n s i t e c o n d i t i o n s . A d v i c e i s a l s o g i v e n on p r o p e r sample h a n d l i n g , f i e l d d e t e r m i n a t i o n s , QA/QC p r o c e d u r e s , p e r s o n n e l s a f e t y measures, and documentation. Planned a r e a s o f e x p a n s i o n i n c l u d e s u r f a c e - w a t e r s a m p l i n g and s o i l o r g a n i c contaminant sampling a p p l i c a t i o n s . ESES c h a r a c t e r i s t i c s , as w e l l as those o f t h e n e x t two systems d e s c r i b e d , a r e summarized i n T a b l e 1. Smart Method Index A s i g n i f i c a n t number o f sample a n a l y s e s f o r e n v i r o n m e n t a l m o n i t o r i n g a r e p e r f o r m e d under l e g i s l a t i v e mandate. EPA i s r e q u i r e d t o m o n i t o r waste s i t e s and t h e q u a l i t y o f t h e environment i n g e n e r a l . P o l l u t a n t g e n e r a t o r s , h a n d l e r s , and d i s p o s e r s a r e r e q u i r e d by r e g u l a t i o n t o monitor t h e i r operations. I n f a c t , l e g i s l a t i o n i s a



Analytical Method Selection

SMI

Data Validation

Sampling Plan Preparation/ Review

ESES

CADRE

DOMAIN

SYSTEM

Pascal

Object-Oriented Programming

IBM-PC

IBM-PC

Natural Language Understanding

Mainframe/Mini

SAS

Pascal

Prolog

AI TECHNIQUES Rule-driven Inference

PLATFORM IBM-PC 286/386

KnowledgePro

LANGUAGE/ TOOL

Data Security

User-customizable

Easy Query

Centralization

Modularization

Hypergraphics

Hypertext

FEATURES

T a b l e 1. C h a r a c t e r i s t i c s o f Q u a l i t y A s s u r a n c e E x p e r t Systems Described



76


c a t a l y s t f o r a n a l y t i c a l methods development and improvement. A t the same t i m e , the s t a t e o f c u r r e n t l y a v a i l a b l e c a p a b i l i t i e s i s a l i m i t i n g f a c t o r f o r the l e v e l s o f r e g u l a t o r y m o n i t o r i n g r e q u i r e d . I n f o r m a t i o n on a v a i l a b i l i t y , c h a r a c t e r i s t i c s , a p p l i c a b i l i t y , and performance o f a n a l y t i c a l methods i s o f t e n i n c o n s i s t e n t and n o t r e a d i l y a c c e s s i b l e . Method i n f o r m a t i o n i s fragmented throughout EPA program documentation and between o t h e r a g e n c i e s and i n s t i t u t i o n s . A needs assessment s t u d y , performed t o s u p p o r t the EPA E x p e r t System I n i t i a t i v e , i n d i c a t e d a h i g h p r i o r i t y f o r the development o f an i n t e l l i g e n t method i n d e x . Some b e n e f i t s e x p e c t e d from t h i s system a r e f a s t e r and b e t t e r method s e l e c t i o n , use o f more a p p r o p r i a t e DQOs, r e d u c t i o n o f d u p l i c a t i o n o f e f f o r t , and the i d e n t i f i c a t i o n o f areas f o r f u r t h e r research. The Smart Method Index (SMI) system i s d e s i g n e d t o s o r t o p t i o n s a c c o r d i n g t o i n f o r m a t i o n need, a n a l y t e s , m a t r i x , performance, a p p l i c a b l e r e g u l a t i o n s , and o t h e r c r i t e r i a and t o r e t r i e v e f o r the u s e r a n a l y t i c a l methods a p p l i c a b l e t o the problem (7) . The SMI u s e r base may i n c l u d e a n a l y t i c a l c h e m i s t s , r e s e a r c h e r s , p r o j e c t managers, i n d u s t r y p e r s o n n e l , l e g i s l a t i v e s t a f f , and concerned citizens. E s s e n t i a l d e s i g n r e q u i r e m e n t s a r e comprehensiveness, a c c e s s i b i l i t y , and r e l a t i v e ease o f use. The c u r r e n t development f o c u s e s on a h y b r i d implementation. A c e n t r a l i z e d d a t a base manager i n a mainframe computer i s r e m o t e l y a c c e s s e d v i a a microcomputer-based smart u s e r i n t e r f a c e . N a t u r a l language t e c h n i q u e s are b e i n g i n v e s t i g a t e d t o p r o v i d e the u s e r w i t h an E n g l i s h - l i k e query f a c i l i t y . T h i s microcomputer-based component i s b e i n g d e v e l o p e d i n P r o l o g language. I t has the f u n c t i o n o f t r a n s l a t i n g the u s e r ' s query t o the code t h a t w i l l cause the d a t a base management system to r e t r i e v e the d e s i r e d d a t a . Widely experienced a n a l y t i c a l c h e m i s t s are i n v o l v e d i n the s p e c i f i c a t i o n o f the b a s i c E n g l i s h q u e r i e s t o be s u p p o r t e d by the system. The c o n t e n t s o f a l r e a d y e x i s t i n g method d a t a bases i n EPA are b e i n g i n t e g r a t e d w i t h SMI, thus a v o i d i n g d u p l i c a t i o n o f c o s t s on d a t a g a t h e r i n g . An added b e n e f i t f o r the u s e r s i s the a b i l i t y t o query a number o f d i f f e r e n t d a t a bases through a s i n g l e i n t e r f a c e . The need o f a l a r g e number of u s e r s t o a c c e s s t h i s l a r g e d a t a base makes c e n t r a l i z a t i o n a must because the l o g i s t i c s o f d i s t r i b u t i o n would be practically i n s u r m o u n t a b l e . T h i s approach i s a l s o c o n s i s t e n t w i t h the n e c e s s i t y for "instant updating." A secondary o b j e c t i v e o f t h i s p r o j e c t i s t o e x p l o r e the development o f e x p e r t systems i n a mainframe p l a t f o r m i n the EPA network. Intelligent system components p r o t o t y p e d in the microcomputer c o u l d be implemented on a mainframe computer. This i s an a l t e r n a t i v e t o the expense o f mainframe development t h a t has d e t e r r e d the i m p l e m e n t a t i o n o f e x p e r t systems f o r t h i s p l a t f o r m a t EPA. The r e l a t i v e l y h i g h c o s t o f e x p e r t system development t o o l s f o r mainframe computers c o u l d be o b v i a t e d by t r a n s f e r r i n g e x p e r t system s h e l l s developed by o t h e r Government a g e n c i e s t o the EPA. Some o f the c h o i c e s a r e CLIPS, developed by the N a t i o n a l A e r o n a u t i c s and Space A d m i n i s t r a t i o n , and LES (Lockheed Expert System), d e v e l o p e d by Lockheed w i t h i n Department o f Defense p r o j e c t s .


5.


Sampling, Analysis, and Data Validation


Computer-Aided Data Review and E v a l u a t i o n Most Superfund d a t a a r e o b t a i n e d through the EPA C o n t r a c t L a b o r a t o r y Program (CLP). Data a r e produced by a p p r o x i m a t e l y one hundred independent l a b o r a t o r i e s and u t i l i z e d by t h e t e n EPA Regions. The r e s u l t s o f the a n a l y s e s a r e r o u t i n e l y r e v i e w e d and v a l i d a t e d a g a i n s t s t a n d a r d c r i t e r i a t o a s s u r e t h a t they a r e o f known q u a l i t y , a p p l i c a b l e f o r t h e i r i n t e n d e d use, and l e g a l l y a d m i s s i b l e ( 8 . 9 ) . Data r e v i e w and e v a l u a t i o n has been d e t e r m i n e d t o be r a t e l i m i t i n g i n t h e d a t a g e n e r a t i o n p r o c e s s due t o i t s l a b o r - i n t e n s i v e nature. EPA Regions accumulate a b a c k l o g o f s e v e r a l thousand samples f o r r e v i e w . I n some i n s t a n c e s t h e r e v i e w i s n o t as thorough as i n t e n d e d due t o t h e t r a d e o f f o f completeness and a c c u r a c y f o r timeliness. The Computer-Aided Data Review and E v a l u a t i o n (CADRE) system a s s i s t s i n the v a l i d a t i o n and r e p o r t i n g o f i n f o r m a t i o n by automating most o f t h e QA/QC checks f o r e l e c t r o n i c a l l y d e l i v e r e d d a t a ( 1 0 ) . F i g u r e 2 shows t h e i n t e g r a t i o n o f CADRE i n t h e g e n e r a l CLP d a t a f l o w , i n c l u d i n g the mainframe-based CLP A n a l y t i c a l R e s u l t s Data Base (CARD). CADRE f o l l o w s g e n e r a l d a t a v a l i d a t i o n r u l e s d e t e r m i n e d by the EPA A n a l y t i c a l Operations Branch and R e g i o n a l offices, complemented w i t h t h e judgement o f CLP methods q u a l i t y assurance e x p e r t s . I t c a n be c u s t o m i z e d by each R e g i o n t o accommodate l o c a l c o n d i t i o n s , s p e c i a l p r o j e c t needs, and non-CLP d a t a . In this d e c e n t r a l i z e d environment, c a p a b i l i t i e s f o r u s e r c u s t o m i z a t i o n a r e an e s s e n t i a l requirement f o r t h e system u t i l i z a t i o n . The microcomputer p l a t f o r m , s e l e c t e d f o r CADRE development and d e l i v e r y , i s i d e a l f o r t h i s type o f a p p l i c a t i o n . O b j e c t - o r i e n t e d programming t e c h n i q u e s ( a s an e x t e n s i o n t o t h e P a s c a l programming language) a r e b e i n g a p p l i e d i n CADRE because o f the advantage o f r e - u s i n g p i e c e s o f code i n d i f f e r e n t v e r s i o n s w i t h m i n i m a l reprogramming. T h i s programming t e c h n i q u e makes p i e c e s o f code and d a t a "smart;" they a c t as e n t i t i e s w i t h t h e d e t a i l s o f t h e i r i n n e r workings h i d d e n from t h e o u t s i d e . Code s e c t i o n s pass "messages" t o each o t h e r and respond t o t h e o t h e r code s e c t i o n messages t o make t h e o v e r a l l assembly work. The CADRE CLP ORGANIC v e r s i o n automates the p r o c e s s o f v a l i d a t i o n o f o r g a n i c a n a l y s i s d a t a ( v o l a t i l e , s e m i v o l a t i l e , and p e s t i c i d e compounds). CADRE CLP INORGANIC and Quick Turnaround CADRE, a r e under development t o automate v a l i d a t i o n o f i n o r g a n i c d a t a and Q u i c k Turnaround Methods data, r e s p e c t i v e l y . Other Developments Other a r t i f i c i a l i n t e l l i g e n c e t e c h n i q u e s t h a t a r e b e i n g i n v e s t i g a t e d a t t h e L a s Vegas l a b o r a t o r y i n c l u d e t h e a p p l i c a t i o n o f a d a p t i v e n e u r a l networks t o p a t t e r n r e c o g n i t i o n o f mass s p e c t r a o f o r g a n i c compounds. T h i s a p p l i c a t i o n c o u l d s e r v e as a complement t o t h e c u r r e n t l i b r a r y s e a r c h method f o r i d e n t i f y i n g unknown p o l l u t a n t s by gas chromatography/mass s p e c t r o m e t r y a n a l y s i s . The l i b r a r y s e a r c h method may m i s i d e n t i f y compounds due t o shortcomings i n t h e s e a r c h a l g o r i t h m o r t o sample c o m p l e x i t y ( e . g . , c o e l u t i o n o f a n a l y t e s ) . The s p e c t r a i n t h e p r e s e n t NIST/EPA l i b r a r y i n c l u d e over 50,000 e n t r i e s . An e f f e c t i v e p a t t e r n r e c o g n i t i o n method c o u l d p r o v i d e a t


77


F i g u r e 2. C o n t r a c t L a b o r a t o r y V a l i d a t i o n w i t h CADRE.

Program Computer-Aided Data


δ

H

ρ

r

>

as M

ο

w

Ο *5

*i

H H

H

M

w

οο


5.



l e a s t a c h e m i c a l c l a s s i d e n t i f i c a t i o n , g i v i n g some i n f o r m a t i o n as to i t s p o t e n t i a l f o r e n v i r o n m e n t a l impact. L a b o r a t o r y performance e v a l u a t i o n systems a r e b e i n g d e s i g n e d and d e v e l o p e d (11) t o h e l p m o n i t o r and q u a l i f y t h e performance o f l a b o r a t o r i e s i n t h e CLP and t o a s s i s t i n t h e s e l e c t i o n o f a p p r o p r i a t e l a b o r a t o r i e s f o r c o n t r a c t i n g a n a l y t i c a l work o f a s p e c i f i c nature. Both the e v a l u a t i o n o f l a b o r a t o r i e s f o r p a r t i c i p a t i o n i n an e n v i r o n m e n t a l i n v e s t i g a t i o n and m o n i t o r i n g o f the f a c i l i t y d u r i n g o p e r a t i o n a r e s i g n i f i c a n t a s p e c t s o f t h e d a t a c o l l e c t i o n p r o c e s s . The development o f performance-based a n a l y t e and m a t r i x - s p e c i f i c q u a l i t y c o n t r o l components o f a n a l y t i c a l methods i s e s s e n t i a l t o the i d e n t i f i c a t i o n o f confidence l i m i t s f o r both d e t e c t i o n and q u a n t i f i c a t i o n o f contaminants. C u r r e n t knowledge ( e . g . , i n s t r u m e n t performance c r i t e r i a ) and areas o f r e s e a r c h ( e . g . , s u r r o g a t e / a n a l y t e c o r r e l a t i o n ) c a n be i n t e g r a t e d i n an e x p e r t system a p p r o p r i a t e f o r t h e e v a l u a t i o n o f l a b o r a t o r y , method, and program performance. A system u t i l i z i n g s i m i l a r components f o r the e v a l u a t i o n o f i n i t i a l performance on a q u a l i f i c a t i o n sample i s a p p r o p r i a t e as a p r i m a r y c o n s i d e r a t i o n i n t h e s e l e c t i o n o f a c o n t r a c t o r f a c i l i t y . Other c o n s i d e r a t i o n s t h a t may be a p p r o p r i a t e i n c l u d e p o t e n t i a l c o n f l i c t o f i n t e r e s t , c o s t , p r o x i m i t y t o s i t e , and analytical capacity. Summary and D i s c u s s i o n D e v e l o p e r s o f e x p e r t systems f o r t h e EPA must r e c o g n i z e i m p o r t a n t Agency c o n s i d e r a t i o n s , such as t h e v a r y i n g n a t u r e o f t h e problems addressed, a s t a f f w i t h d i v e r s e experience, d e c e n t r a l i z a t i o n o f t a s k s , computer r e s o u r c e c o n s t r a i n t s , g e o g r a p h i c a l d i s t a n c e , and high personnel turnover. D u r i n g t h e d e s i g n phase, c l o s e a t t e n t i o n s h o u l d be p a i d t o s e l e c t i n g t h e a p p r o p r i a t e d e l i v e r y environment f o r each system's t a r g e t u s e r base. E x p e r t systems p r e s e n t p a r t i c u l a r difficulty because o f t h e h i g h demand on computer r e s o u r c e s a s s o c i a t e d w i t h t h i s type o f s o f t w a r e . I t i s d i f f i c u l t t o f i t e x p e r t systems i n t o computer hardware t h a t must a l s o be used f o r r o u t i n e t a s k s . A t t h e same t i m e , t h e i n t r o d u c t i o n o f s p e c i a l i z e d p l a t f o r m s f o r d e l i v e r y o f e x p e r t systems would be c o s t l y and would p r e s e n t an acceptance p r o b l e m w h i c h might p r e v e n t i n t e g r a t i o n o f e x p e r t systems i n t o t h e mainstream EPA computing environment t o g e t h e r w i t h o t h e r d a t a h a n d l i n g and a n a l y s i s s o f t w a r e . An e f f o r t has been made t o p r o v i d e c o m p a t i b l e , i f n o t s t a n d a r d , user interfaces across different systems (e.g., menu-driven i n t e r f a c e s ) . T h i s i s more d i f f i c u l t when e x p e r t system development s h e l l s , w i t h t h e i r own s p e c i f i c s , a r e u s e d f o r development. Many a s p e c t s o f e x p e r t systems, i n c l u d i n g o p e r a t i o n , documentation, and system l i f e c y c l e management, do n o t l e n d themselves v e r y w e l l t o a h i g h l e v e l o f s t a n d a r d i z a t i o n . An i m p o r t a n t c o n s i d e r a t i o n i n s t a n d a r d i z i n g development i s compliance w i t h EPA system l i f e c y c l e management g u i d e l i n e s ( 1 2 ) . These g u i d e l i n e s a r e s t a t e d i n g e n e r a l terms and a s s u r e t h a t a p p r o p r i a t e c o n s i d e r a t i o n has been g i v e n t o c o s t - b e n e f i t c o n c e r n s , t o p r o j e c t r e l e v a n c e , and t o f u n d i n g o f development and maintenance. T h e i r p r i m a r y purpose i s t o ensure t h a t t h e system w i l l a d e q u a t e l y p e r f o r m t h e f u n c t i o n f o r w h i c h i t



80


was i n t e n d e d . W i t h t h i s i n mind, t h e g e n e r a l system l i f e c y c l e management r e q u i r e m e n t s must be c u s t o m i z e d o r a d j u s t e d , t o a degree, f o r each system t o a c h i e v e i t s g o a l s , w h i l e a t t h e same time a v o i d i n g i n c r e a s i n g the development c o s t beyond t h e p o i n t o f diminishing return. The n a t u r e o f e x p e r t systems and t h e i r development p r o c e s s presents p a r t i c u l a r d i f f i c u l t i e s f o r the a p p l i c a t i o n o f the t r a d i t i o n a l method o f v a l i d a t i n g s o f t w a r e a g a i n s t comprehensive p r e s p e c i f i c a t i o n s , s i n c e the f i n a l l e v e l o f o p e r a t i o n o f an e x p e r t system i s d i f f i c u l t t o p r e - d e t e r m i n e . T e s t i n g by m e a s u r i n g the degree o f c o m p a r a b i l i t y o f the system's performance t o the performance o f human domain e x p e r t s , by u s i n g a r e p r e s e n t a t i v e s e t o f p r o b l e m c a s e s , i s more p r a c t i c a l and more i n tune w i t h the d e f i n i t i o n o f e x p e r t systems. Expert systems are a promising approach to improving e n v i r o n m e n t a l d a t a g e n e r a t i o n i n terms o f q u a l i t y , t i m e l i n e s s , and c o s t - e f f e c t i v e n e s s . Improvements i n t h i s c r u c i a l a r e a o f a c t i v i t y w i l l b e n e f i t n o t o n l y the d a t a c o l l e c t i o n programs, b u t a l s o w i l l i n c r e a s e the e f f i c i e n c y and e f f e c t i v e n e s s o f r e m e d i a l programs. Notice The i n f o r m a t i o n i n t h i s document has been funded w h o l l y o r i n p a r t by t h e U n i t e d S t a t e s E n v i r o n m e n t a l P r o t e c t i o n Agency under c o n t r a c t number 68-03-3249 t o Lockheed E n g i n e e r i n g & S c i e n c e s Company. I t has been s u b j e c t e d t o Agency r e v i e w and approved f o r p u b l i c a t i o n . M e n t i o n o f t r a d e names o r commercial p r o d u c t s does n o t c o n s t i t u t e endorsement o r recommendation f o r use.

Literature Cited 1. Development of Data Quality Objectives (internal document), U.S. Environmental Protection Agency, Quality Assurance Management Staff, Washington, DC, 1986. 2. Data Quality Objectives for Remedial Response Activities-Development Process, EPA/540/G-87/003, U.S. Environmental Protection Agency, Office of Solid Waste and Emergency Response, Washington, DC, 1987. 3. Olivero, R. Α.; York, K. R.; Homsher, M. T.; Cabble, K. J . , A Hypertext-Based System for Planning of Environmental Sampling Projects, In Proc. 4th Annual Lockheed A r t i f i c i a l Intelligence Symp., Calabasas, California, 1989, pp 4-81 - 4-91. 4. KnowledgePro User Manual, Version 1.4, Knowledge Garden, Inc., Nassau, New York, 1988. 5. Olivero, R. Α.; Cameron, R. E.; Cabble, K. J.; Homsher, M. T.; Stapanian, M. A.; Brown, K. W., Environmental Field Sampling Expert System--Development of a Soil Sampling Advisor, In Proc. 1st I n t l . Symp. on Field Screening Methods for Hazardous Waste Site Investigations, Las Vegas, Nevada, 1988, pp 325-339. 6. Cameron, R. E.; Olivero, R. Α.; Cabble, K. J.; Carlsen, C.; Teubner, M. D.; Bottrell, D. W.; Homsher, M. T., An Expert System Approach for Selection of Sampling Methods for GroundWater Contamination at Hazardous Sites, In Proc. of the I n t l .



5.

OLIVERO A N D BOTTRELL

Sampling, Analysis, and Data Validation

81

Conf. Chemistry for the Protection of the Environment. Lublin, Poland, 1989. 7. Olivero, R. Α.; Boyd, J. L.; Bottrell, D. W.; Homsher, M. T., A Smart System for Selecting Analytical Methods for Environmental Analysis--Concept and Design, In Proc. 5th Annual Waste Testing and Quality Assurance Symp., U.S. Environmental Protection Agency, Washington, DC, 1989, pp I-217 - I-226. 8. Hellmann, Μ. Α.; Cheatham, R. Α., Data Validation--Its Importance i n Health Risk Assessments, Environ. Sci. Technol., 1989, 23(6), pp 638-640. 9. Fairless, B. J.; Bates, D. I., Estimating the Quality of Environmental Data, Pollution Engineering, 1989, pp 108-111. 10. Shumann, C. R.; Olivero, R. Α.; Homsher, M. T.; Petty, J. D., Automation of Regional Data Validation, In Symposium on Waste Testing and Quality Assurance: Third Volume, ASTM STP 1075, D. Friedman, Ed.; American Society for Testing and Materials, Philadelphia, 1989. 11. Homsher, M. T.; Olivero, R. Α.; Robertson, G. L.; Moore, J. M.; Fisk, J . F., Development of an Expert System for the Analysis of Laboratory Performance Evaluation Data, In Proc. 3rd Annual Lockheed A r t i f i c i a l Intelligence and Strategic Computing Symp., Houston, Texas, 1987. 12. System Life Cycle Management Guidance Practice Paper for Expert Systems. U.S. Environmental Protection Agency, Office of Solid Waste and Emergency Response, Washington, DC, 1988. RECEIVED March 12, 1990


Expert Systems To Support Environmental ... - ACS Publications

Recommend Documents