how it works
CARMA provides advice about both rangeland and cropland grasshopper infestations.
CARMA's rangeland module uses case-based reasoning to produce advice
about the most economical responses to grasshopper infestations based
on roughly 140 combined years of entomologist expertise shared among
eight experts. CARMA does this by predicting the proportion of
available forage that will be consumed by grasshoppers and estimating
the economic returns of various treatment options. Tests have shown
that CARMA's grasshopper forage consumption predictions, which are the
core of determining the best course of action, very closely
approximate the median predictions of the experts. CARMA gives advice
by comparing the current infestation to previous infestations (i.e.,
cases) and adapting the recommendations of the experts to fit the
current infestation. The information required to make the forage loss
prediction includes the date, the infestation location, the range
value and infestation history of the location, the number of
grasshoppers per square yard, the grasshopper type and age
distribution, the relative recent precipitation and temperatures, and
the total area infested (including adjacent neighbors' lands).
Infestation probabilities for your location and the effectiveness of
each treatment type are used to predict the future probabilities of
re-infestation for each treatment type, and statistical methods are
used to predict the range of economic benefits for each treatment
option. Finally, a set of rules are used to select the possible
CARMA also includes a prototype crop protection module that gives advice
about cropland grasshopper infestations using accepted cropland
Further information about CARMA is contained in the following sources:
John D. Hastings, Alexandre V. Latchininsky, and Scott Schell, Sustainability of Grasshopper Management and Support through CARMA, Proceedings of the 42nd Hawaii International Conference on System Sciences (HICSS-42), Waikoloa Village, Big Island, HI, January 5-8, 2009, recipient of a Best Paper Award.
Alexandre Latchininsky, John Hastings, and Scott Schell, Good CARMA for the High Plains, Proceedings of the 2007 Americas' Conference on Information Systems (AMCIS 2007), Keystone, Colorado, August 9-12, 2007.
John Hastings, Karl Branting, Jeffrey Lockwood, and Scott Schell, CARMA+: A General Architecture for Pest Management, Proceedings of the Workshop on Environmental Decision Support Systems, Eighteenth International Joint Conference on Artificial Intelligence (IJCAI-2003), Acapulco, Mexico, August 9-15, 2003.
John Hastings, Karl Branting, and Jeffrey Lockwood, CARMA: A
Case-Based Rangeland Management Adviser, AI Magazine, 23(2):
Karl Branting, John Hastings, and Jeffrey Lockwood, CARMA: A
Case-Based Range Management Advisor, Proceedings of The Thirteenth
Innovative Applications of Artificial Intelligence Conference
(IAAI-2001), Seattle, Washington, August 7-9, 2001.
L. Karl Branting, John D. Hastings, and Jeffrey A. Lockwood,
Integrating Cases and Models for Prediction in Biological Systems,
AI Applications, 11(1):29-48 (1997).
John Hastings, Karl Branting, and Jeff Lockwood, A Multi-Paradigm
Reasoning System for Rangeland Management, Computers and
Electronics in Agriculture, 16(1):47-67 (1996).
John D. Hastings, L. Karl Branting, and Jeffrey A. Lockwood, Case
Adaptation Using an Incomplete Causal Model, Proceedings of the
First International Conference on Case-Based Reasoning (ICCBR-95), Sesimbra,
Portugal, October 23-26, 1995.
John D. Hastings and L. Karl Branting, Global and Case-Specific
Model-based Adaptation, Proceedings of the AAAI 1995 Fall Symposium
on Adaptation of Knowledge for Reuse, Cambridge, Massachusetts,
November 10-12, 1995.
L. Karl Branting and John D. Hastings, An Empirical Evaluation of
Model-Based Case Matching and Adaptation, Proceedings of the
Workshop on Case-Based Reasoning, Twelfth National Conference on
Artificial Intelligence (AAAI-94), Seattle, Washington, July 31-August 4, 1994.
© 2002-2019 John Hastings