Filtern
Dokumenttyp
- Wissenschaftlicher Artikel (11)
- Dissertation (1)
Schlagworte
- Fernerkundung (7)
- Satellitenfernerkundung (3)
- Lidar (2)
- machine-learning (2)
- stem detection (2)
- tree inclination (2)
- ALS (1)
- Ausgangsgestein (1)
- Autokorrelation (1)
- BRDF (1)
- Baum (1)
- Biogasgewinnung (1)
- Boden (1)
- Bodenerosion (1)
- Bodengefüge (1)
- Bodengüte (1)
- Bodennutzung (1)
- Crop classification (1)
- Deep learning (1)
- Degradation (1)
- Detektion (1)
- Energiepflanzenbau (1)
- Ernährungssicherung (1)
- Feldfrucht (1)
- Flugkörper (1)
- GPS (1)
- Humus (1)
- Hyperspektraler Sensor (1)
- Infrarotthermographie (1)
- Klassifikation (1)
- Kriging (1)
- Landnutzung (1)
- LiDAR (1)
- MODIS (1)
- Maisanbau (1)
- Maissilage (1)
- Maschinelles Lernen (1)
- Mineral (1)
- Multispektralfotografie (1)
- Nachhaltigkeit (1)
- Nationalpark Hunsrück-Hochwald (1)
- Nutzpflanzen (1)
- Orientierung (1)
- Provinz Copperbelt (1)
- Regression Kriging (1)
- Rheinland-Pfalz (1)
- Sambia (1)
- Spatial autocorrelation (1)
- Spektroradiometrie (1)
- Stamm Botanik (1)
- Thermalluftbild (1)
- Trier (1)
- UAV (1)
- Wald (1)
- Waldinventur (1)
- Wasserstress (1)
- Weinbau (1)
- aggregate stability (1)
- airborne LiDAR (1)
- annual energy crops (1)
- biogas (1)
- biomethantion (1)
- co-registration (1)
- crop stress (1)
- deep learning (1)
- degradation (1)
- drought (1)
- emissivity (1)
- environmental impact (1)
- evapotranspiration (ET) modeling (1)
- food security (1)
- forest (1)
- forest inventory (1)
- geometric (1)
- hyperspectral (1)
- image segmentation (1)
- individual tree detection (1)
- land use (1)
- land-use change (1)
- land-use intensity microbial biomass (1)
- miombo woodland (1)
- multispectral (1)
- perennial energy crops (1)
- permanent grassland (1)
- phototropism (1)
- point set registration (1)
- regeneration (1)
- remote sensing (1)
- risk assessment (1)
- satellite TIR mission (1)
- sentinel 1 (1)
- sub-Saharan Africa (1)
- temperature (1)
- thermal infrared (TIR) (1)
- thermal remote sensing (1)
- tree matching (1)
- viticulture (1)
- water stress (1)
- water use (1)
Institut
In order to discuss potential sustainability issues of expanding silage maize cultivation in Rhineland-Palatinate, spatially explicit monitoring is necessary. Publicly available statistical records are often not a sufficient basis for extensive research, especially on soil health, where risk factors like erosion and compaction depend on variables that are specific to every site, and hard to generalize for larger administrative aggregates. The focus of this study is to apply established classification algorithms to estimate maize abundance for each independent pixel, while at the same time accounting for their spatial relationship. Therefore, two ways to incorporate spatial autocorrelation of neighboring pixels are combined with three different classification models. The performance of each of these modeling approaches is analyzed and discussed. Finally, one prediction approach is applied to the imagery, and the overall predicted acreage is compared to publicly available data. We were able to show that Support Vector Machine (SVM) classification and Random Forests (RF) were able to distinguish maize pixels reliably, with kappa values well above 0.9 in most cases. The Generalized Linear Model (GLM) performed substantially worse. Furthermore, Regression Kriging (RK) as an approach to integrate spatial autocorrelation into the prediction model is not suitable in use cases with millions of sparsely clustered training pixels. Gaussian Blur is able to improve predictions slightly in these cases, but it is possible that this is only because it smoothes out impurities of the reference data. The overall prediction with RF classification combined with Gaussian Blur performed well, with out of bag error rates of 0.5% in 2009 and 1.3% in 2016. Despite the low error rates, there is a discrepancy between the predicted acreage and the official records, which is 20% in 2009 and 27% in 2016.
Production of biomass feedstock for methanation in Europe has focused on silages of maize and cereals. As ecological awareness has increased in the last several years, more attention is being focused on perennial energy crops (PECs). Studies of specific PECs have shown that their cultivation may enhance agrobiodiversity and increase soil organic carbon stocks while simultaneously providing valuable feedstock for methanation. This study was designed to compare soil quality indicators under annual energy crops (AECs), PECs and permanent grassland (PGL) on the landscape level in south-western Germany. At a total 25 study sites, covering a wide range of parent materials, the cropping systems were found adjacent to each other. Stands were commercially managed, and PECs included different species such as the Cup Plant, Tall Wheatgrass, Giant Knotweed, Miscanthus, Virginia Mallow and Reed Canary Grass. Soil sampling was carried out for the upper 20 cm of soil. Several soil quality indicators, including soil organic carbon (Corg), soil microbial biomass (Cmic), and aggregate stability, showed that PECs were intermediate between AEC and PGL systems. At landscape level, mean Corg content for (on average) 6.1-year-old stands of PEC was 22.37 (±7.53) g kg1, compared to 19.23 (±8.08) and 32.08 (±10.11) for AEC and PGL. Cmic contents were higher in PECs (356 ± 241 lgCg1) compared to AECs (291 ± 145) but significantly lower than under PGL (753 ± 417). The aggregate stability increased by almost 65% in PECs compared to AEC but was still 57% lower than in PGL. Indicator differences among cropping systems were more pronounced when inherent differences in the parent material were accounted for in the comparisons. Overall, these results suggest that the cultivation of PECs has positive effects on soil quality indicators. Thus, PECs may offer potential to make the production of biomass feedstock more sustainable.