Search

Seasonal climate forecasts are commonly based on model runs from fully coupled forecasting systems that use Earth system models to represent interactions between the atmosphere, ocean, land and other Earth-system components. Recently, machine learning (ML) methods are increasingly being investigated for this task where large-scale climate variability is linked to local or regional temperature or precipitation in a linear or non-linear fashion. This paper investigates the use of interpretable ML methods to predict seasonal precipitation for East Africa in an operational setting. Dimension reduction is performed by decomposing the precipitation fields via empirical orthogonal functions (EOFs), such that only the respective factor loadings need to the predicted. Indices of large-scale climate variability--including the rate of change in individual indices as well as interactions between different indices--are then used as potential features to obtain tercile forecasts from an interpretable ML algorithm. Several research questions regarding the use of data and the effect of model complexity are studied. The results are compared against the ECMWF seasonal forecasting system (SEAS5) for three seasons--MAM, JJAS and OND--over the period 1993-2020. Compared to climatology for the same period, the ECMWF forecasts have negative skill in MAM and JJAS and significant positive skill in OND. The ML approach is on par with climatology in MAM and JJAS and a significantly positive skill in OND, if not quite at the level of the OND ECMWF forecast.

We present a general and intuitive ambiguity model for intersections, junctions and other structures in binary edge images. The model is combined with edge tracing, where edges are ordered sequences of connected pixels. The objective is to provide a versatile preprocessing method for tasks such as figure-ground segmentation, object recognition, topological analysis, etc. By using only a small set of straightforward principles, the results are intuitive to describe. This helps to implement subsequent processing steps, such as resolving ambiguous edge connections at junctions. By using an augmented edge map, neighboring edges can be directly accessed using quick local search operations. The edge tracing uses recursion, which leads to compact programming code. We explain our algorithm using pseudocode, compare it with related methods, and show how simple modular postprocessing steps can be used to optimize the results. The complete algorithm, including all data structures, requires less than 50 lines of pseudocode. We also provide a C++ implementation of our method., Comment: 14 pages

Agricultural food production and natural ecological systems depend on a range of seasonal climate indicators that describe seasonal patterns in climatological conditions. This paper proposes a probabilistic forecasting framework for predicting the end of the freeze-free season, or the time to a mean daily near-surface air temperature below 0 $^\circ$C (here referred to as hard freeze). The forecasting framework is based on the multi-model seasonal forecast ensemble provided by the Copernicus Climate Data Store and uses techniques from survival analysis for time-to-event data. The original mean daily temperature forecasts are statistically post-processed with a mean and variance correction of each model system before the time-to-event forecast is constructed. In a case study for a region in Fennoscandia covering Norway for the period 1993-2020, the proposed forecasts are found to outperform a climatology forecast from an observation-based data product at locations where the average predicted time to hard freeze is less than 40 days after the initialization date of the forecast on October 1.

Weather-related risk makes the insurance industry inevitably concerned with climate and climate change. Buildings hit by pluvial flooding is a key manifestation of this risk, giving rise to compensations of the induced physical damages and business interruptions. In this work, we establish a nationwide, building-specific risk score for water damage associated with pluvial flooding in Norway. We fit a generalized additive model that relates the number of water damages to a wide range of explanatory variables that can be categorized into building attributes, climatological variables and topographical characteristics. The model assigns a risk score to every location in Norway, based on local topography and climate, which is not only useful for insurance companies, but also for city planning. Combining our model with an ensemble of climate projections allows us to project the (spatially varying) impacts of climate change on the risk of pluvial flooding towards the middle and end of the 21st century.

We introduce a class of proper scoring rules for evaluating spatial point process forecasts based on summary statistics. These scoring rules rely on Monte-Carlo approximations of expectations and can therefore easily be evaluated for any point process model that can be simulated. In this regard, they are more flexible than the commonly used logarithmic score and other existing proper scores for point process predictions. The scoring rules allow for evaluating the calibration of a model to specific aspects of a point process, such as its spatial distribution or tendency towards clustering. Using simulations we analyze the sensitivity of our scoring rules to different aspects of the forecasts and compare it to the logarithmic score. Applications to earthquake occurrences in northern California, USA and the spatial distribution of Pacific silver firs in Findley Lake Reserve in Washington, USA highlight the usefulness of our scores for scientific model selection.

Statistical functionals are called elicitable if there exists a loss or scoring function under which the functional is the optimal point forecast in expectation. While the mean and quantiles are elicitable, it has been shown in Heinrich (2014) that the mode cannot be elicited if the true distribution can follow any Lebesgue density. We strengthen this result substantially, showing that the mode cannot be elicited if the true distribution is any distribution with continuous Lebesgue density and unique local maximum. Likewise, the mode fails to be identifiable relative to this class., Comment: 10 pages, 1 figure

Artificial visual attention systems aim to support technical systems in visual tasks by applying the concepts of selective attention observed in humans and other animals. Such systems are typically evaluated against ground truth obtained from human gaze-data or manually annotated test images. When applied to robotics, the systems are required to be adaptable to the target system. Here, we describe a flexible environment based on a robotic middleware layer allowing the development and testing of attention-guided vision systems. In such a framework, the systems can be tested with input from various sources, different attention algorithms at the core, and diverse subsequent tasks.

Region-based artificial attention constitutes a framework for bio-inspired attentional processes on an intermediate abstraction level for the use in computer vision and mobile robotics. Segmentation algorithms produce regions of coherently colored pixels. These serve as proto-objects on which the attentional processes determine image portions of relevance. A single region---which not necessarily represents a full object---constitutes the focus of attention. For many post-attentional tasks, however, such as identifying or tracking objects, single segments are not sufficient. Here, we present a saliency-guided approach that groups regions that potentially belong to the same object based on proximity and similarity of motion. We compare our results to object selection by thresholding saliency maps and a further attention-guided strategy.