Efficient improvement of silage additives by using genetic algorithms

The enormous variety of substances which may be added to forage in order to manipulate and improve the ensilage process presents an empirical, combina torial optimization problem of great complexity. To investigate the utility of genetic algorithms for designing effective silage additive combinations , a series of small-scale proof of principle silage experiments were perfor med with fresh ryegrass, Having established that significant biochemical ch anges occur over an ensilage period as short as 2 days, we performed a seri es of experiments in which we used 50 silage additive combinations (prepare d by using eight bacterial and other additives, each of which was added at six different levels, including zero [i.e., no additive]). The decrease in pH, the increase in lactate concentration, and the free amino acid concentr ation were measured after 2 days and used to calculate a "fitness" value th at indicated the quality of the silage (compared to a control silage made w ithout additives). This analysis also included a "cost" element to account for different total additive levels. In the initial experiment additive lev els were selected randomly, but subsequently a genetic algorithm program wa s used to suggest new additive combinations based on the fitness values det ermined in the preceding experiments. The result was very efficient selecti on for silages in which large decreases in pH and high levels of lactate oc curred along with low levels of free amino acids. During the series of Eve experiments, each of which comprised 50 treatments, there was a steady incr ease in the amount of lactate that accumulated; the best treatment combinat ion was that used in the last experiment, which produced 4.6 times more lac tate than the untreated silage. The additive combinations that were found t o yield the highest fitness values in the final (fifth) experiment were ass essed to determine a range of biochemical and microbiological quality param eters during full-term silage fermentation. We found that these combination s compared favorably both with uninoculated silage and crith a commercial s ilage additive. The evolutionary computing methods described here are a con venient and efficient approach for designing silage additives.