Fakultät Agrarwissenschaften

Permanent URI for this communityhttps://hohpublica.uni-hohenheim.de/handle/123456789/9

Die Fakultät entwickelt in Lehre und Forschung nachhaltige Produktionstechniken der Agrar- und Ernährungswirtschaft. Sie erarbeitet Beiträge für den ländlichen Raum und zum Verbraucher-, Tier- und Umweltschutz.

Homepage: https://agrar.uni-hohenheim.de/

Browse

Browsing Fakultät Agrarwissenschaften by Classification "000"

Type the first few letters and click on the Browse button
Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    Management effects on the performance of double cropping systems - results from a multi-site experiment
    (2022) Schmidt, Fruzsina; Böhm, Herwart; Piepho, Hans-Peter; Urbatzka, Peer; Wachendorf, Michael; Graß, Rüdiger
    Traditional (silage) maize production often has negative side-effects related to unprotected soil surface. There are several possibilities to enhance system sustainability through reducing soil disturbance. However, implementation may be hindered due to reduced nitrogen availability and increased weed infestation, especially in organic agriculture. A field experiment to evaluate yield potential of 18 silage maize cropping systems under organic management was conducted at three distinct locations. Examined parameters were first crop, maize and total harvested dry matter yield (DMY), and maize dry matter content (DMC). Treatment factors included first crop (FC—winter pea, hairy vetch, and their mixtures with rye, control (SCS), management—incorporating FC use and tillage (double cropping system no-till (DCS NT), double cropping system reduced till (DCS RT), double cropped, mulched system terminated with roller-crimper (DCMS Roll), SCS control), fertilization, mechanical weed control—and row width (75 cm, 50 cm). A high variation among environments occurred, but similar patterns manifested across locations: Number of crops in the rotation had a high influence, followed by management and FC. Row width had only marginal and inconsistent effect. FC mixtures generally yielded higher than pure legumes. Maize DMY in DCS, DCMS was lower than or comparable to SCS. Maize DMC were environment-specifically below acceptable range, especially under DCMS. Total harvested DMY in DCS were similar to or greater than SCS. Results suggest differences from the optimization of farming operations for one (SCS) or two crops (DCS, DCMS) with strong effects at early maize development and on the length of season. FC use and tillage factors possibly altered the soil water, temperature, and mineralization dynamics, resulting in modified maize growth. DCS RT and DCMS Pure performed with the best maize yields, improved soil protection, and tillage reduction in the silage maize part of the rotation under organic management. However, alternative management systems, especially under DCS NT and DCMS (Mix) with studied maize maturity classes are less suited, particularly in cool and wet spring conditions, because of a potentially slower development of FC, a later establishment of maize plants and therefore, a shorter growing season for the maize crop.
  • Thumbnail Image
    Publication
    Mechanisms to alleviate over-generalization in XCS for continuous-valued input spaces
    (2022) Wagner, Alexander R. M.; Stein, Anthony
    In the field of rule-based approaches to Machine Learning , the XCS classifier system (XCS) is a well-known representative of the learning classifier systems family. By using a genetic algorithm (GA), the XCS aims at forming rules or so-called classifiers which are as general as possible to achieve an optimal performance level. A too high generalization pressure may lead to over-general classifiers degrading the performance of XCS. To date, no method exists for XCS for real-valued input spaces (XCSR) and XCS for function approximation (XCSF) to handle over-general classifiers ensuring an accurate population. The Absumption mechanism and the Specify operator, both developed for XCS with binary inputs, provide a promising basis for over-generality handling in XCSR and XCSF. This paper introduces adapted versions of Absumption and Specify by proposing different identification and specialization strategies for the application in XCSR and XCSF. To determine their potential, the adapted techniques are evaluated in different classification problems, i.e., common benchmarks and real-world data from the agricultural domain, in a multi-step problem as well as different regression tasks. Our experimental results show that the application of these techniques leads to significant improvements of the accuracy of the generated classifier population in the applied benchmarks, data sets, multi-step problems and regression tasks, especially when they tend to form over-general classifiers. Furthermore, considering the working principle of the proposed techniques, the intended decrease in overall classifier generality can be confirmed.