No abstract

Abstract:In agriculture, reducing herbicide use is a challenge to reduce health and environmental risks while maintaining production yield and quality. Site-specific weed management is a promising way to reach this objective but requires efficient weed detection methods. In this paper, an automatic image processing has been developed to discriminate between crop and weed pixels combining spatial and spectral information extracted from four-band multispectral images. Image data was captured at 3 m above ground, with a camera (multiSPEC 4C, AIRINOV, Paris) mounted on a pole kept manually. For each image, the field of view was approximately 4 m × 3 m and the resolution was 6 mm/pix. The row crop arrangement was first used to discriminate between some crop and weed pixels depending on their location inside or outside of crop rows. Then, these pixels were used to automatically build the training dataset concerning the multispectral features of crop and weed pixel classes. For each image, a specific training dataset was used by a supervised classifier (Support Vector Machine) to classify pixels that cannot be correctly discriminated using only the initial spatial approach. Finally, inter-row pixels were classified as weed and in-row pixels were classified as crop or weed depending on their spectral characteristics. The method was assessed on 14 images captured on maize and sugar beet fields. The contribution of the spatial, spectral and combined information was studied with respect to the classification quality. Our results show the better ability of the spatial and spectral combination algorithm to detect weeds between and within crop rows. They demonstrate the improvement of the weed detection rate and the improvement of its robustness. On all images, the mean value of the weed detection rate was 89% for spatial and spectral combination method, 79% for spatial method, and 75% for spectral method. Moreover, our work shows that the plant in-line sowing can be used to design an automatic image processing and classification algorithm to detect weed without requiring any manual data selection and labelling. Since the method required crop row identification, the method is suitable for wide-row crops and high spatial resolution images (at least 6 mm/pix).

Nutrient fluxes were determined in a chronosequence of Douglas-fir stands in the Beaujolais Mounts (France). Annual and seasonal variations occurred during the 3 years of investigation; fluxes were generally highest in autumn-winter.Atmospheric inputs were among the mean values from a monitoring network of forest ecosystems in France. Nutrient outputs from the soil profile were higher than average and occurred mainly during vegetation dormancy.Mean input-output budgets were negative for N, S, K, Ca and Mg, characterising an imbalance of the site chemistry dynamics. The P budget was positive. Most of the nutrient output from the ecosystem occurred as losses in the drainage water. These losses were related to excess nitrification and consecutive cation mobilisation throughout the soil profile.Surface water, however, had a neutral pH and very low nitrate and aluminium contents, which may have been buffered by the subsoil.Budgets differed between stands and tended to be more negative in the youngest stand. Part of this behaviour was related to stand age and part to the former land use of plots. Theoretical budgets were calculated for forest rotation lengths of 20, 40 and 60 years; it was concluded that shorter rotations would increase nutrient losses. The trend of a decrease in budget deficits with stand age suggests that the effect of vegetation change will be reduced at the next rotation but the impact of stand development may remain.Predicted nutrient budgets for a second 60 year Douglas-fir rotation suggested that available Ca in the soil would be depleted and that this depletion would be even more drastic if whole tree harvesting were adopted.In conclusion, Douglas-fir stands introduced changes in soil function that may impoverish the soil if present trends remain the same over the next forest rotations. The maintenance of sustainability will require nutrient input by fertilisation.