Markus Sökefeld

Detection and Identification of Weeds

This chapter reviews the approaches for the automation of weed detection. Site-specific plant protection needs to address the varying weed infestation, but the automation is only partially solved and research is still ongoing. The properties for plant species distinction as well as approaches that use them are presented. The focus is on image based methods, of which an example is given.

Variable Rate Technology for Herbicide Applicationherbicide application

Variable rate technology (VRT ) is used for the application of various agricultural inputs in order to respond adequately to the within-field variability of environmental factors like soil properties, incidence of pests and crop parameters. The areas in plant production in which VRTs are used are highlighted. For the variable rate application of herbicides commercial as well as research solutions are described. The use of VRT for herbicide treatment with regard to pre-emergence and post-emergence applications and the requirements are described. The potential of further herbicides savings due to an additional variation of herbicidal ingredients in consideration of herbicide sensitivity of single weed species and groups of weed species, respectively is shown and evaluated.

Camera steered mechanical weed control in sugar beet, maize and soybean

In sugar beet, maize and soybean, weeds are usually controlled by herbicides uniformly applied across the whole field. Due to restrictions in herbicide use and negative side effects, mechanical weeding plays a major role in integrated weed management (IWM). In 2015 and 2016, eight field experiments were conducted to test the efficacy of an OEM Claas 3-D stereo camera® in combination with an Einböck Row-Guard® hoe for controlling weeds. Ducks-foot blades in the inter-row were combined with four different mechanical intra-row weeding elements in sugar beet, maize and soybean and a band sprayer in sugar beet. Average weed densities in the untreated control plots were from 12 to 153 plants m−2 with Chenopodium album, Polygonum convolvulus, Thlapsi arvense being the most abundant weed species. Camera steered hoeing resulted in 78% weed control efficacy compared to 65% using machine hoeing with manual guidance. Mechanical intra-row elements controlled up to 79% of the weeds in the crop rows. Those elements did not cause significant crop damage except for the treatment with a rotary harrow in maize in 2016. Weed control efficacy was highest in the herbicide treatments with almost 100% followed by herbicide band-applications combined with inter-row hoeing. Mechanical weed control treatments increased white sugar yield by 39%, maize biomass yield by 43% and soybean grain yield by 58% compared to the untreated control in both years. However, yield increase was again higher with chemical weed control. In conclusion, camera guided weed hoeing has improved efficacy and selectivity of mechanical weed control in sugar beet, maize and soybean.