Search

In this paper a new tool for simultaneous optimisation of decisions on multiple time scales is presented. The tool combines the dynamic properties of Markov decision processes with the flexible and compact state space representation of LImited Memory Influence Diagrams ( Limids). A temporal version of Limids, TemLimids, is defined by adding time-related functions to utility nodes. As a result, expected discounted utility, as well as expected relative utility might be used as optimisation criteria in TemLimids. Optimisation proceeds as in ordinary Limids. A sequence of such TemLimids can be used to model a Markov Limid Process, where each TemLimid represents a macro action. Algorithms are presented to find optimal plans for a sequence of such macro actions. Use of algorithms is illustrated based on an extended version of an example from pig production originally used to introduce the Limid concept. [ABSTRACT FROM AUTHOR]

In agriculture Markov decision processes (MDPs) with finite state and action space are often used to model sequential decision making over time. For instance, states in the process represent possible levels of traits of the animal and transition probabilities are based on biological models estimated from data collected from the animal or herd. State space models (SSMs) are a general tool for modeling repeated measurements over time where the model parameters can evolve dynamically. In this paper we consider methods for embedding an SSM into an MDP with finite state and action space. Different ways of discretizing an SSM are discussed and methods for reducing the state space of the MDP are presented. An example from dairy production is given. [ABSTRACT FROM AUTHOR]

During the past two decades there has been growing public and political awareness of the consequences of eutrophication in Denmark. By the mid-1980s, the environmental status of inland and coastal waters had deteriorated due to high nutrient loads. Consequently, a number of different Action Plans against water pollution were introduced. In the agricultural sector, focus has been on reductions in nitrogen leaching obtained by the introduction of various measures: a maximum limit to the density of livestock, 9 months’ storage capacity for manure, catch crops for at least 6% of the land, enhanced utilization (up to 75%) of nitrogen in manure, etc. The agricultural sector in Denmark has implemented all of these measures, and as a result of the effort, the target for reductions in nitrogen leaching will be reached. Currently, the total loss of nitrogen from farmland is likely to be reduced by approximately 50% compared to the level in the mid-1980s. Some of the measures have been fair and based on sound arguments, and have been implemented with only minor difficulties, whereas others have proved troublesome and in our opinion disproportionately expensive. Today, further general regulation with equal restrictions toward all farmers regardless of differences in environmental impacts is no longer an acceptable path to follow. In the future, it will be necessary to pinpoint new measures in the most sensitive areas, where the potential for further reductions in nutrient loads is large. Danish Agriculture calls for specific actions—and consequently a shift in environmental management and policy making. Such a revised management strategy is the only path to follow in order to obtain further improvements in environmental conditions. Meanwhile, future development in the agricultural sector will be possible and a win–win situation can be reached. [ABSTRACT FROM AUTHOR]