Browsing by Author "Orti, Miguel Vallejo"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Temporal statistical analysis and predictive modelling of drought and flood in Rundu–Namibia
    (Namibia University of Science and Technology, 2019-08) Orti, Miguel Vallejo; Negussie, Kaleb
    Namibia is a semi-arid country characterized by the alternation of long drought periods and short episodes of intense rain, which often causes great stress to plants, animals and people. Thus, a deep understanding of the spatio-temporal distribution of rainfall is required to minimize their negative impacts, affecting food security. The temporal occurrence of drought and rainy events in the North East of Namibia (Rundu area) is described and studied for a series of monthly rainfall from 1940 until 2015. Inter-arrival times analysis is conducted to model the occurrence of extreme (high and low) rainfall events through a Poisson Point Process (PPP). Adapting the definitions of drought and flood to the water demands of crops in Rundu, it is deduced that the average inter-arrival time for droughts is smaller than for rainy years, presenting 3 and 10 years respectively. Results of PPP are presented on Lorenz Curves for different study cases (more than one, two and three events per time unit). From the PPP results it can be extracted that the probability of suffering a drought in a period of 5 years in Rundu is approximately 70%, while this likelihood is only 40% for floods. Considering the occurrence of three or more events in a time period of 10 years, the probability is almost 50% for drought and less than 10% floods. Point Process (PP) analysis demonstrates that Poisson Distribution can be used to model the occurrence of drought and floods in Rundu area, being especially precise to model the presence of one event in periods between 1 and 10 years.
  • Thumbnail Image
    Item
    Use of TanDEM-X and Sentinel Products to Derive Gully Activity Maps in Kunene Region (Namibia) Based on Automatic Iterative Random Forest Approach
    (2021) Orti, Miguel Vallejo; Winiwarter, Lukas; Corral-Pazos-de-Provens, Eva; Williams, Jack G; Bubenzer, Olaf; Höfle, Bernhard
    Gullies are landforms with specific patterns of shape, topography, hydrology, vegetation, and soil characteristics. Remote sensing products (TanDEM-X, Sentinel-1, and Sentinel-2) serve as inputs into an iterative algorithm, initialized using a micromapping simulation as training data, to map gullies in the northwestern of Namibia. A Random Forest Classifier examines pixels with similar characteristics in a pool of unlabeled data, and gully objects are detected where high densities of gully pixels are enclosed by an alpha shape. Gully objects are used in subsequent iterations following a mechanism where the algorithm uses the most reliable pixels as gully training samples. The gully class continuously grows until an optimal scenario in terms of accuracy is achieved. Results are benchmarked with manually tagged gullies (initial gully labeled area <0.3% of the total study area) in two different watersheds (408 and 302 km2, respectively) yielding total accuracies of>98%, with 60% in the gully class, Cohen Kappa >0.5, Matthews Correlation Coefficient >0.5, and receiver operating characteristic Area Under the Curve >0.89. Hence, our method outlines gullies keeping low false-positive rates while the classification quality has a good balance for the two classes (gully/no gully). Results show the most significant gully descriptors as the high temporal radar signal coherence (22.4%) and the low temporal variability in Normalized Difference Vegetation Index (21.8%). This research builds on previous studies to face the challenge of identifying and outlining gully-affected areas with a shortage of training data using global datasets, which are then transferable to other large (semi-) arid regions