Course curriculum

Create a study plan adjusted to your interests. Linking Data Science to specialization...

The Master's Data Science in Agriculture, Food, Forests and Environment, with a duration of 2 years, allows the creation of a study plan adjusted to the student's area of interest. The course has the following structure:

7 mandatory curricular units

Block dedicated to learning and practice about data science fundamentals and methodologies.

44 ECTS credits

See

5 optional curricular units

A set of optional curricular units selected by the student to deepen the specialization in the area of interest.

30 ECTS credits

See

Dissertation / Project / Internship

Final component of the study plan, to explore a specific topic whose presentation and evaluation leads to a master's degree.

46 ECTS credits

Progress in practice-based learning

The master's emphasizes practice as a teaching methodology. In the curricular units dedicated to data science, the time of face-to-face teaching in the classroom is reduced, in favor of exercises and autonomous practical work by the students.

The hands-on learning experience is also facilitated by an environment of tools and methodologies that are common to all data science curricular units. In this way, students progress in learning, from data management, programming, analysis and visualization, and modeling and machine learning, while deepening the use of the key tools used by the data science communities (e.g., python, jupyter notebook, Google colab, SQL, pandas, numpy, scikit-learn, or others that emerge in the meantime).

Learning also includes the promotion of soft skills. The use of collaborative tools will be constant in all phases of the course, including the sharing of code and solutions in the cloud, and the use of discussion forums. In Hackathon Project, students create multidisciplinary teams, in which solutions will be developed for problems proposed by partner companies of the master's degree.

Increase knowledge in specialization

Students can define their specialty profile by selecting 5 curricular units (30 ECTS), from the list of options available for the master's degree. These units are based on and shared with several ISA masters, which guarantee the highest quality training in the fields of agriculture, food, forests and the environment.

These specialty units, however, allow an extension of the application of data science methodologies, which is used in part of the practical component, in applications that demonstrate the power of its application.

Structure

Curricular Unit   Credits
1st year / 1st semester    
Fundamentals of agro-environmental Data Science Mandatory 6
Syllabus
  1. Definition of Data Science;
  2. Fundamentals, solutions and examples of application in the digital transition in food production, management of natural resources and the environment;
  3. Overview of Data science topics and algorithms;
  4. Data science methodology;
  5. Data science methodological phases;
  6. Understanding the areas of application, acquisition, preparation and analysis of data, modeling, evaluation, implementation, reporting and feedback;
  7. Brief introduction to the data science tools and potential application to each phase of the methodology;
  8. Introduction to Big Data Analysis and Cloud Computing;
  9. Availability of data resources;
  10. Ethics in accessing and using information.
See at Fenix
Introduction to Python Mandatory 6
Syllabus
  1. Installing and configuring a python interpreter and development environments, with emphasis on collaborative environments;
  2. Introduction to python and algorithms. Basics of python programming (variables, operators, conditions, loops, functions, dataTypes, etc);
  3. Structuring a program. Library import and code reuse;
  4. File handling (read-write), directories and access and handling of large files;
  5. Interaction with command line execution arguments;
  6. Access and provide a data service (APIs);
  7. Structuring of a program for processing in sequence and in parallel and in a grid environment.
See at Fenix
Data Management and Storage Mandatory 6
Syllabus
  1. Introduction to data management and data management systems;
  2. Types of databases;
  3. Concept of relational databases;
  4. SQL language and application for creating and using databases;
  5. Main open-source and proprietary database technologies;
  6. NoSQL systems and their application;
  7. Data quality principles, vocabularies and ontologies;
  8. Tools and resources for checking data quality, organization and normalization;
  9. Use of global and resolvable unique identifiers, traceability;
  10. Agri-environment data resources;
  11. Introduction to the concept of large data sets and their specificities in relation to production, storage and analysis.
See at Fenix
Option 1   6
Option 2   6
1st year / 2nd semester    
Analysis and Visualization of Complex Agro-Environmental Data Mandatory 6
Syllabus
  1. Main tools for data analysis and visualization using Python (Pandas, Plotly, Matplotlib, Seaborn, Bokeh, geoplotlib);
  2. Data types and variable identification;
  3. Statistical summary;
  4. Empirical data distribution;
  5. Standardization and data transformation;
  6. Reduction of data dimensionality: multivariate ordination methods;
  7. Correlation and regression analysis;
  8. Design principles applied to information visualization;
  9. Uni, bi and multivariate graphical visualization;
  10. Advanced representations of information;
  11. Representation of spatial data;
  12. Creation of interactive visual information panels (dashboards).
See at Fenix
Applied Machine Learning Mandatory 6
Syllabus
  1. What is machine learning? First examples;
  2. Classification and clustering problems;
  3. Extraction of variables and organization of input data;
  4. Binary response variable: decision and risk rule;
  5. Classifier quality assessment: errors of omission and errors of commission;
  6. Categorical answer variable: decision trees;
  7. "Ensemble" of classifiers: "random forests";
  8. Neural networks;
  9. Convolutional networks and deep learning for image problems.
See at Fenix
Option 3   6
Option 4   6
Option 5   6
     
2nd year    
Data Science Seminar Mandatory 2
Syllabus
  1. Prepare synthetic presentations of data science application cases related to the topic to be developed in the master's dissertation;
  2. Present the student's dissertation work in a compact format, supported by advanced data visualization;
  3. Develop presentation skills.
See at Fenix
Data Science Hackathon Project Mandatory 12
Syllabus

Development of a project proposed by partner companies, in the form of hackathon, in teams consisting of the following profiles: i) domain specialist; ii) team coordinator; iii) analyst; iv) programmer; v) reporter/communicator. The curricular unit will have an initial seminar to present the problems proposed by the companies, which will be complemented on the characterization of how the hackathon project works. This seminar will include the following contents:

  1. characterization of a hackathon project;
  2. roles, characterization and responsibilities of team members;
  3. tools for collaborative development of code, documentation and information;
  4. definition of objectives and goals in a data science project.

These contents will be complemented with syllabus adjusted to the specific project, either from the data science skills, or from the specific components of the system under analysis.

See at Fenix
Dissertation/Project/Internship Final project 46

Optional curricular units

Curricular unit Area
Applied Operations Research Transversal
Syllabus

Basic concepts and application examples in four main topics:

  1. linear programming;
  2. network models;
  3. integer programming;
  4. multi-criteria decision analysis.
See at Fenix
Statistics and Experimental Design Transversal
Syllabus
  1. 1) Hypothesis tests for count data, based on Pearson's Chi-squared statistic;
  2. Simple Linear Regression (both descriptive and inferential contexts);
  3. Multiple Linear Regression (both descriptive and inferential contexts);
  4. Analysis of Variance (introductory concepts in experimental design; Anova models for some elementary experimentaldesigns).
See at Fenix
Fertilizers and Fertilizing Techniques Agronomic Engineering
Syllabus

Fertilizers, classification, characteristics, criteria for selection and risks associated with their use: “conventional” mineral fertilizers, “special” mineral fertilizers (containing secondary macronutrients and micronutrients, chelated, stabilized, slow release, controlled release, biofertilizer), organic and mineral-organic fertilizers. Mineral amendments. Organic amendments, valorization of organic waste (animal manures, waste from agricultural and food industries, composted MSW and sewage sludge). Fertilization in soil grown crops: recommendations based on soil analysis and plant analysis, base dressing, top dressing, fertigation and foliar fertilization, fertilization plans for selected crops. Fertilizing in soilless culture systems: soilless culture techniques, substrates for soilless culture, water quality, nutrient solutions. Visits to farms.

See at Fenix
Crop Protection Agronomic Engineering
Syllabus

Characterization and typification of the agro-ecosystem; characterization of the key-enemies of different crops (pests, diseases and weeds), symptoms and damages, life cycles, epidemiology and population dynamics, natural enemies; methods of risk estimation and decision-making tools; strategies and management tactics of protection. I. Protection of vegetables and cereal crops. The following crops are addressed: Protected and open-air vegetable crops (lettuce, cabbages, cucumbers, potatoes and tomatoes), and cereals (rice, corn, wheat, barley and oats). II. Protection of erennial woody crops. The following woody crops are addressed: Grapevine, citrus, apple, pear and stone fruits.

See at Fenix
Irrigation and Drainage Agronomic Engineering
Syllabus

Irrigation design and irrigation scheduling: aims and contexts (soil, climate). Biophysical background, identification of pre-requisites. Measuring water use and water stress, methods, limitations and contexts of application. Modelling water use. Crop water requirements: nomenclature and models. Reference evapotranspiration, crop coefficients (single and dual), stress coefficients. Deficit irrigation. Water stress indicators and other tools for irrigation scheduling. Water use and irrigation efficiencies. Water productivity. Irrigation methods. Quality parameters. Sprinkler, drip, pivot and surface irrigation. Control and automatisms, pumping systems. Drainage: systems, equipments, measurements necessary for design. Applications and special cases. Project exercise: from climate, crop and soil to the irrigation project (students working in group present all calculations, a descriptive memory and a power point presentation discussed in class.

See at Fenix
Industrial Plant Design Food Engineering
Syllabus

The Food Engineering Project: Market analysis; Business strategy; Financing. Strategic Coordination in Project Development. Different phases: Preliminary Program and Project Team; Base Program: analysis of the conditionings and territorial framework. Prior Study - technical and economic feasibility. Basic project of Architecture. Licensing. Financial support, tax incentives. Execution project. Final Surveys. Authorization of Labor. Company strategy: Big data, type of products and quantity to produce as a market function; technologies; technological diagrams and mass balances; sizing and selection of equipment. Distribution in space, lay-out sketch. Estimated costs. Case studies - main technological indices and equipment. Practical exercise: Previous study of the Food Industry Facilities Project using the bottom up approach: starting from market share - up to consumer needs (big data)- to reception of raw materials, production flows, digital networks, etc.

See at Fenix
Food Quality Systems Food Engineering
Syllabus
  1. Quality: Concepts and models; Quality and business strategies; Quality management.
  2. Portuguese Quality System / European Quality System: Certification and Accreditation
  3. Quality Management Systems: ISO 9001
  4. Quality Improvement Programs - Total Quality Model E.F.Q.M .; Lean Manufacturing: Principles; DMAIC; Kaisen Methodology.
  5. Quality Assessment: Self-evaluation; Quality Costs; Quality Audit.
  6. Most relevant references in the area of Food Safety: ISO 22000 - steps of implementation of the benchmark and analysis of the requirements.
  7. Food safety references: IFS, BRC, FSSC 22000 - analysis of requirements and standards comparison.
  8. Global GAP - importance of certification in the primary sector.
  9. Food defense - approach to food defense plans and specific requirements in the frameworks under study.
See at Fenix
Marketing Food Engineering
Syllabus
  1. 1. Marketing Strategy and Orientation
  2. 1.1 Introduction to Marketing
  3. 1.2 Evolution of Marketing
  4. 1.3 Marketing Orientation
  5. 1.4 Marketing Process
  6. 1.5 Concepts of Management and Strategic Planning
  7. 1.6 Marketing Strategy Formulation
  8. 2. Consumer Behavior and Market Segmentation
  9. 2.1 Determinants of Consumer Behavior
  10. 2.2 Purchase Decision Process
  11. 2.3 Segmentation Criteria
  12. 2.4 Target Market Selection
  13. 2.5 Positioning Strategies
  14. 3. Introduction to Marketing Research
  15. 3.1 Marketing Research Objectives
  16. 3.2 Marketing Research Methods
  17. 4. Marketing Policies: Marketing-Mix
  18. 4.1 Product: concepts, components (brand, packaging), innovation
  19. 4.2 Price: concepts, stages and methods
  20. 4.3 Distribution: organization and dynamics of distribution, distribution mix
  21. 4.4 Communication: objectives, strategy and communication mix.
  22. 5. Marketing Plan
  23. 5.1 Definition of the Marketing Plan
  24. 5.2 Steps of the Planning Process
See at Fenix
Environmental Modelling Environmental Engineering
Syllabus
  1. Module 1 – Modeling and Model Building
  2. 1.1. Models and modelling
  3. 1.2. Visualizing environmental data1.3. Processing environmental data
  4. Practical case-studies
  5. 1.4. Wind speed and wind power
  6. 1.5. Solar radiation at Earth’s surface
  7. 1.6. Light interaction with a plant canopy
  8. Module 2 – Hydrodynamic and habitat models for river restoration
  9. Module 3 – Empirical modelling in R
  10. Module 4 – The SWAT+ model (Soil and Water Assessment Tool)
See at Fenix
Project - Environment Environmental Engineering
Syllabus
  1. The Project goals and content. General aspects and fundamentals. Legislation on public works - Ordinance No. 701-H/2008 of 29 July.
  2. Preparation and design of a technical proposal.
  3. Project organization and specifications (written content and drawings). Specifications – general clauses and technical clauses. Technical assistance. Considerations on Tender Programs and Contract Specifications
  4. Technical evaluation of projects. Evaluation criteria (technical quality, price, deadline, others)
  5. Focal aspects on measurements and budget estimation.
  6. Economic and financial study. Cost recovery principle. Application of environmental and economic indicators
  7. Ethics and deontology in engineering projects
  8. Computer-aided design program. Application in engineering of the Autocad program. Drawing files, extensions, “viewers”, layouts, viewports. Configuration and customization of user interface, command bars, shortcuts, console commands; Organization and referencing of the design; Graphic entities and the management of their properties, blocks, data entry, identifying dimensions, quoting drawings, printing and plotting elements.
See at Fenix
Solid Waste Treatment Technologies Environmental Engineering
Syllabus
  1. 1. Origin, characteristics and properties of solid waste
  2. 1.1 Classification according the origin
  3. 1.2 Classification according the characteristics
  4. 1.3 Physical, chemical and biochemical properties
  5. 1.4 Quantification and physical characterization
  6. 2. Physical, physic-chemical and chemical processes for solid waste treatment
  7. 2.1 Manual and mechanical separation
  8. 2.2 Drying and densification
  9. 2.3 Incineration e co-incineration
  10. 2.4 Pyrolysis and plasma technology
  11. 3. Advanced biological processes for solid waste treatment
  12. 3.1 Aerobic
  13. 3.2 Anaerobic
  14. 3.3 Combined aerobic/anaerobic
  15. 4. Other processes for solid wastes treatment and valorization
  16. 4.1 Acid, alkaline and enzymatic hydrolysis
  17. 4.2. Production of glucose, ethanol, methanol and single cell protein
  18. 5 – Key parameters for the assessment of efficiency and selection of waste treatment technologies
  19. Case Study: Mechanical Biological Treatment (MBT) in a Municipal Solid Waste System
  20. Practical classes (laboratorial classes and study visits)
See at Fenix
Environmental Economics and Natural Resources Environmental Engineering
Syllabus
  1. 1. An introduction to environmental and natural resource economics
  2. Economy and the environment. Economic functions of the environment. Scarcity, choice and opportunity cost. Pareto optimum and compensation tests. Externalities, public goods and market failure.
  3. 2. Environmental and natural resource use problems as economic problems
  4. Pollution and pollution control. Economic efficiency, cost-effectiveness, technological innovation and other assessment criteria. Compared analysis of different pollution control tools. Biodiversity, ecosystem services and their economic value. Renewable natural resources: optimal use and common pool resources. Optimal forest management. Time, dynamic efficiency and sustainability.
  5. 3. Analytical tools and environmental policy decision-making
  6. Cost-benefit analysis and the economic valuation of the environment as decision-support tools in environmental and natural resource management and policy. Role and the limits of economic analysis.
See at Fenix
Remote Sensing and Image Analysis Forest Engineering and Natural Resources
Syllabus

Introduction to the raster structure of multispectral data. Spatial, radiometric, spectral and temporal resolution. Color compositing and image visualization. Contrast enhancement and filtering. Pre-processing: radiometric correction and DN-to-reflectance conversion. Geometrical correction. The atmospheric effect and its correction in images. Spectral signatures: vegetation, soil, and water. Main algorithms for supervised and unsupervised classification: ISODATA, k-means, maximum likelihood, classification trees. Accuracy assessment statistics. Change detection and analysis of image time series. Vegetation indices: generic concept and specialized indices; minimization of disturbances induced by the atmosphere and soil background.

See at Fenix
Forest Models Forest Engineering and Natural Resources
Syllabus
  1. 1. Overview of forest models and simulators as a support to sustainable forest management
  2. 2. Data for the development and validation of forest models: permanent, interval plots and temporary plots; continuous forest inventory; total and partial stem analysis
  3. 3. Forest productivity evaluation: factors influencing forest productivity and productivity management; evaluation of forest productivity
  4. 4. Introduction to R and RStudio
  5. 5. Allometric relationships and growth functions: theoretical growth functions; simultaneous modelling of several individuals: formulating growth functions without age explicit
  6. 6. The FCTOOLS website, the sIMfLOR platform and the standsSIM-md simulator
  7. 7. Growth and yield models
  8. - Stand models: GLOBULUS
  9. - Stand models with simulation of diameter distribution: PBRAVO
  10. - Individual tree models: PINASTER, PINEA, CASTANEA, SUBER
  11. 8. Management oriented process based models: 3PG model
  12. 9. Regional and large scale simulators
  13. 10. Evaluation/validation of models
See at Fenix
Fire Ecology and Management Forest Engineering and Natural Resources
Syllabus

Introduction to the rural fire problem in Portugal: statistics on number of fires, area burned and causes of ignition. Geographical distribution. Plants as fuels: main types of forest fuels. Structural and thermodynamical parameters of plant fuels – fuel modelling; Climate, meteorology, and fire. Main synoptical conditions associated with large fires. Fire danger indexing: the Canadian Fire Weather Index (FWI). Wildfire behavior: ignition, steady-state fire behavior, and extreme fire behavior. Crown fires. Wind-dominated vs plume-dominated fires. Fire behavior modeling: the Rothermel model and simulation with BEHAVE. Fire ecology and effects. Fire as an ecosystem disturbance. Fire effects on flora, fauna, soils and water. Fire prevention silviculture. Stand and landscape-level fuels and forest management.

See at Fenix
Functional Processes in Forest Ecosystems Forest Engineering and Natural Resources
Syllabus
  1. I. Water. Effects of vegetation on the water balance.
  2. II. Carbono e Solo. Vegetação e sequestro de carbono. Disponibilidade de nutrientes e crescimento das plantas. Interações solo-raízes.
  3. III. Biodiversity and species interaction.
See at Fenix
Management and Conservation of Freshwater Ecosystems Biodiversity and Conservation
Syllabus
  1. I- Hydro-geomorphic and hydraulic scenario. Mineralization and major components. Thermal and chemical stratifications in aquatic environment. Majority and minority components, gases. Mineralization and organic matter. Organic matter. Elements of variable proportionality and microcomponents. Portuguese fish fauna. Species and guilds. Biological communities, typology and functioning of river ecosystems. Spatial, temporal and trophic gradients.
  2. II- Qualidade da água. Formas de poluição. Restauro de albufeiras e oligotrofização. Regularização, alterações do regime de caudais e extracção de água. Caudais ecológicos. Situação em Portugal e formas de implementação de caudais de manutenção ecológica. Passagens p/ peixes, tipologia, localização e dimensionamento. Estrutura e ecologia ripárias. Papel e valor da mata ripária. Restauro da vegetação ripária. Alterações morfológicas do canal e leitos fluviais. Extracção de inertes. Efeitos e formas de mitigar alterações. Restoration of habitats, sections and river segments. Assessment of water quality, ecological and fish. Official indices and their calculation.
See at Fenix
Animal Population Ecology and Management Biodiversity and Conservation
Syllabus

Analyzing population responses to the environment drivers. Demographic strategies. Interspecific relationships: cooperation, reproduction, competition. Interspecific relationships. Regulation of populations. Use of RAMAS and VORTEX software in the application of deterministic, stochastic, matrix and metapopulation models using study case. Habitat use and selectivity. Variability and genetic structure of populations, processes of adaptation, isolation and evolution. Estimation of population parameters: analysis of population sampling data. Absolute counts. Distance sampling. Movement and dispersal. Population management: Sustainable exploitation; Conservation and meta-population theory; Management of invasive species. Animal ecology in urban environments. Analysis and management of agricultural and forest habitats for wildlife conservation.

See at Fenix
Management and Conservation of Vegetation and Agroforestry Systems Biodiversity and Conservation
Syllabus
  1. Module 1: Bioclimatic and biogeographic context of Portuguese vegetation; methods of vegetation study.
  2. 1. Bioclimatology and biogeography: history and concepts;
  3. 2. Biomes;
  4. 3. Methods of vegetation study.
  5. Module 2: Vegetation conservation and plant mapping.
  6. 1. Plant mapping;
  7. 2. Biodiversity, vegetation management and conservation;
  8. 3. International Conventions, European Regulations, agri-environmental and forest-environment measures.
  9. Module 3: Agroforestry systems.
  10. 1. Concepts and typologies;
  11. 2. Hydrological balance and nutrient cycling;
  12. 3. Silvopastoral systems: community rural areas as a case study.
  13. Module 4: Restoration and rehabilitation of vegetation and plant communities.
  14. 1. Degradation factors;
  15. 2. Restoration methods; Phytoremediation;
  16. 3. Case studies (riparian galleries; wild fires; weed control; sand dunes; phytoremediation).
See at Fenix
Application

Highlights

  • 2 years training (4 semesters);
  • 5 optional units to deepen areas of application;
  • Data Science core:
    • data science fundamentals and methodologies
    • databases
    • python coding
    • data analysis and visualization
    • machine learning
    • hackathon;
  • Strong practical component: learning by doing.

More about application