Abstract
This work addresses the lot-sizing and scheduling problem under multistage demand uncertainty. A flexible production system is considered, with the possibility to adjust the size and the schedule of lots in every time period based on a rolling-horizon planning scheme. Computationally intractable multistage stochastic programming models are often employed on this problem. An adaptation strategy to the multistage setting for two-stage programming and robust optimization models is proposed. We also present an approximate heuristic strategy to address the problem more efficiently, relying on multistage stochastic programming and adjustable robust optimization. In order to evaluate each strategy and model proposed, a Monte Carlo simulation experiment under a rolling-horizon scheme is performed. Results show that the strategies are promising in solving large-scale problems: the approximate strategy based on adjustable robust optimization has, on average, 6.72% better performance and is 7.9 times faster than the deterministic model.

Abstract
In the retail industry, there are multiple products flowing from different distribution centers to brick-and-mortar stores with distinct characteristics. This industry has been suffering radical changes along the years and new market dynamics are making distribution more and more challenging. Consequently, there is a pressure to reduce shipment sizes and increase the delivery frequency. In such a context, defining the most efficient way to supply each store is a critical task. However, the supply chain planning decision that tackles this type of problem, delivery mode planning, is not well defined in the literature. This paper proposes a definition for delivery mode planning and analyzes multiple ways retailers can efficiently supply their brick-and-mortar stores from their distribution centers. The literature addressing this planning problem is reviewed and the main interdependencies with other supply chain planning decisions are discussed.

Abstract
The present paper proposes two hybrid genetic algorithms as decision-making techniques for operational level decisions in the Glass Container Industry (GCI). The proposed methods address a production scenario where one new furnace and the related machines must be added to the current industrial plant. The configurations for each machine connected in a furnace is a decision to be taken, which depends on demand forecasts for glass containers within a time horizon. It is a tactical and operational level decisions that must be efficiently made. A mathematical formulation is first presented to describe precisely the objective and constraints for such problem. The formulation will also allow solving the problem instances by applying an exact method. Next, a hybrid approach combining genetic algorithms with mathematical programming techniques, and a greedy filter heuristic is proposed to solve the same problem instances. The set of instances is generated with data provided by a GCI located in Portugal and Brazil. The results reported indicate that the hybrid genetic algorithms return solutions able to support the operational and tactical decisions.

Abstract
Background: Ensuring healthcare delivery is dependent both on the prediction of the future demand for healthcare services and on the estimation and planning for the Health Human Resources needed to properly deliver these services. Although the Health Human Resources planning is a fascinating and widely researched topic, and despite the number of methodologies that have been used, no consensus on the best way of planning the future workforce requirements has been reported in the literature. This paper aims to contribute to the extension and diversity of the range of available methods to forecast the demand for Health Human Resources and assist in tackling the challenge of translating healthcare services to workforce requirements. Methods: A method to empirically quantify the relation between healthcare services and Health Human Resources requirements is proposed. For each one of the three groups of specialties identified-Surgical specialties, Medical specialties and Diagnostic specialties (e.g., pathologists)-a Labor Requirements Function relating the number of physicians with a set of specialty-specific workload and capital variables is developed. This approach, which assumes that health managers and decision-makers control the labor levels more easily than they control the amount of healthcare services demanded, is then applied to a panel dataset comprising information on 142 public hospitals, during a 12-year period. Results: This method provides interesting insights on healthcare services delivery: the number of physicians required to meet expected variations in the demand for healthcare, the effect of the technological progress on healthcare services delivery, the time spent on each type of care, the impact of Human Resources concentration on productivity, and the possible resource allocations given the opportunity cost of the physicians' labor. Conclusions: The empirical method proposed is simple and flexible and produces statistically strong models to estimate Health Human Resources requirements. Moreover, it can enable a more informed allocation of the available resources and help to achieve a more efficient delivery of healthcare services.

Abstract
Increasing wildfire threats and costs escalate the complexity of forest fire management challenges, which is grounded in complex interactions between ecological, social, economic, and policy factors. It is immersed in this difficult context that decision-makers must settle on an investment mix within a portfolio of available options, subject to limited funds and under great uncertainty. We model intra-annual fire management as a problem of multistage capacity investment in a portfolio of management resources, enabling fuel treatments and fire preparedness. We consider wildfires as the demand, with uncertainty in the severity of the fire season and in the occurrence, time, place, and severity of specific fires. We focus our analysis on the influence of changes in the volatility of wildfires and in the costs of escaped wildfires, on the postponement of capacity investment along the year, on the optimal budget, and on the investment mix. Using a hypothetical test landscape, we verify that the value of postponement increases significantly for scenarios of increased uncertainty (higher volatility) and higher escape costs, as also does the optimal budget (although not proportionally to the changes in the escape costs). Additionally, the suppression/prevention budget ratio is highly sensitive to changes in escape costs, while it remains mostly insensitive to changes in volatility. Furthermore, we show the policy implications of these findings at operational (e.g., spatial solutions) and strategic levels (e.g., climate change). Exploring the impact of increasing escape costs in the optimal investment mix, we identified in our instances four qualitative system stages, which can be related to specific socioecological contexts and used as the basis for policy (re)design. In addition to questioning some popular myths, our results highlight the value of fuel treatments and the contextual nature of the optimal portfolio mix.

Abstract