Satellite-based forest monitoring: spatial and temporal forecast of growing index and short-wave infrared band.

For detecting anomalies or interventions in the field of forest monitoring we propose an approach based on the spatial and temporal forecast of satellite time series data. For each pixel of the satellite image three different types of forecasts are provided, namely spatial, temporal and combined spatio-temporal forecast. Spatial forecast means that a clustering algorithm is used to group the time series data based on the features normalised difference vegetation index (NDVI) and the short-wave infrared band (SWIR). For estimation of the typical temporal trajectory of the NDVI and SWIR during the vegetation period of each spatial cluster, we apply several methods of functional data analysis including functional principal component analysis, and a novel form of random regression forests with online learning (streaming) capability. The temporal forecast is carried out by means of functional time series analysis and an autoregressive integrated moving average model. The combination of the temporal forecasts, which is based on the past of the considered pixel, and spatial forecasts, which is based on highly correlated pixels within one cluster and their past, is performed by functional data analysis, and a variant of random regression forests adapted to online learning capabilities. For evaluation of the methods, the approaches are applied to a study area in Germany for monitoring forest damages caused by wind-storm, and to a study area in Spain for monitoring forest fires.

[Slaughter findings feedback systems--its use for farms of origin?]. / Schlachtbefundrückmeldesysteme--Nutzen für die Primärproduktion?

Over a period of 22 months 13 official meat inspection authorities examined a number of 152 520 swine at an Austrian slaughterhouse for pathologic-anatomic changes (five parameters). Of those veterinarians whose reliability in the recording of findings was a given, the results were analysed by employing a mathematical model which assessed whether the activities of 25 attending veterinarians and 223 farmers actually lead to an improvement of animal health in their livestock. Mild pneumonia was registered in 14.5% of swine; no attending veterinarians had any influence whatsoever on the occurrence of this parameter. Farmers' activities improved animal health on two farms (0.9%), six farms of origin (2.69%) showed significantly lower findings than the average of all farms. Pleurisy was ascertained in 22% of all slaughter pigs. Through measures taken, four attending veterinarians (16%) caused a reduction of incidents, two works managers (0.9%) made worse, six farmers (2.69%) improved animal health of their live stock. Seven farmers (3.14%) showed significantly (p < 0.05) higher, 28 farms (12.6%) lower prevalence. Pericarditis affected 4.5% of the animals in question. On all farms of origin the condition of health remained unchanged by measures taken by veterinarians. On two farms (0.9%) the influence exercised by farmers led to a deterioration of the health of swine, six businesses (2.69%) showed higher, one (0.45%) lower prevalence than on average. 6.2% of swine showed white spots. Attending veterinarians did not influence this parameter at all. With preventive measures taken five farms (2.24%) showed less, three farms (1.35%) higher prevalence by the end of the 22 month term. Mange concerned 2.2% of all slaughter pigs. The activities of one veterinarian (4%) caused the number of incidents to double; on six farms (2.69%) a significantly higher prevalence was registered. Whatever influence exercised, the status of health of slaughter pigs remained unchanged throughout the duration of the study.