Includes bibliographical references and index.

Introduction -- Why Forecast? -- The Informatics Challenge in Forecasting -- The Model-Data Loop -- Why Bayes? -- Models as Scaffolds -- Case Studies and Decision Support -- Key Concepts -- Hands-on Activities -- From Models to Forecasts -- The Traditional Modeler's Toolbox -- Example; The Logistic Growth Model -- Adding Sources of Uncertainty -- Thinking Probabilistically -- Predictability -- Key Concepts -- Hands-on Activities -- Data, Large and Small -- The Data Cycle and Best Practices -- Data Standards and Metadata -- Handling Big Data -- Key Concepts -- Hands-on Activities -- Scientific Workflows and the Informatics of Model-Data Fusion -- Transparency, Accountability, and Repeatability -- Workflows and Automation -- Best Practices for Scientific Computing -- Key Concepts -- Hands-on Activities -- Introduction to Bayes -- Confronting Models with Data -- Probability 101 -- The Likelihood -- Bayes' Theorem -- Prior Information -- Numerical Methods for Bayes -- Evaluating MCMC Output -- Key Concepts -- Hands-on Activities -- Characterizing Uncertainty -- Non-Gaussian Error -- Heteroskedasticity -- Observation Error -- Missing Data and Inverse Modeling -- Hierarchical Models and Process Error -- Autocorrelation -- Key Concepts -- Hands-on Activities -- Case Study: Biodiversity, Populations, and Endangered Species -- Endangered Species -- Biodiversity -- Key Concepts -- Hands-on Activities -- Latent Variables and State-Space Models -- Latent Variables -- State Space -- Hidden Markov Time-Series Model -- Beyond Time -- Key Concepts -- Hands-on Activities -- Fusing Data Sources -- Meta-analysis -- Combining Data: Practice, Pitfalls, and Opportunities -- Combining Data and Models across Space and Time -- Key Concepts -- Hands-on Activities -- Case Study: Natural Resources -- Fisheries -- Case Study: Baltic Salmon -- Key Concepts -- Propagating, Analyzing, and Reducing Uncertainty -- Sensitivity Analysis -- Uncertainty Propagation -- Uncertainty Analysis -- Tools for Model-Data Feedbacks -- Key Concepts -- Hands-on Activities -- Properties of Means and Variances -- Common Variance Approximations -- Case Study: Carbon Cycle -- Carbon Cycle Uncertainties -- State of the Science -- Case Study: Model-Data Feedbacks -- Key Concepts -- Hands-on Activities -- Data Assimilation 1: Analytical Methods -- The Forecast Cycle -- Kalman Filter -- Extended Kalman Filter -- Key Concepts -- Hands-on Activities -- Data Assimilation 2: Monte Carlo Methods -- Ensemble Filters -- Particle Filter -- Model Averaging and Reversible jump MCMC -- Generalizing the Forecast Cycle -- Key Concepts -- Hands-on Activities -- Epidemiology -- Theory -- Ecological Forecasting -- Examples of Epidemiological Forecasting -- Case Study: Influenza -- Key Concepts -- Assessing Model Performance -- Visualization -- Basic Model Diagnostics -- Model Benchmarks -- Data Mining the Residuals -- Comparing Model Performance to Simple Statistics -- Key Concepts -- Hands-on Activities -- Projection and Decision Support -- Projections, Predictions, and Forecasting -- Decision Support -- Key Concepts -- Hands-on Activities -- Final Thoughts -- Lessons Learned -- Future Directions. Ecologists are being asked to respond to unprecedented environmental challenges. How can they provide the best available scientific information about what will happen in the future? Ecological Forecasting is the first book to bring together the concepts and tools needed to make ecology a more predictive science. Ecological Forecasting presents a new way of doing ecology. A closer connection between data and models can help us to project our current understanding of ecological processes into new places and times. This accessible and comprehensive book covers a wealth of topics, including Bayesian calibration and the complexities of real-world data; uncertainty quantification, partitioning, propagation, and analysis; feedbacks from models to measurements; state-space models and data fusion; iterative forecasting and the forecast cycle; and decision support. Features case studies that highlight the advances and opportunities in forecasting across a range of ecological subdisciplines, such as epidemiology, fisheries, endangered species, biodiversity, and the carbon cycle, Presents a probabilistic approach to prediction and iteratively updating forecasts based on new data, Describes statistical and informatics tools for bringing models and data together, with emphasis on: Quantifying and partitioning uncertainties, Dealing with the complexities of real-world data, Feedbacks to identifying data needs, improving models, and decision support, Numerous hands-on activities in R available online Book jacket.