Giorgio Guariso

• Laurea
• Politecnico di Milano

Convective storms represent a dangerous atmospheric phenomenon, particularly for the heavy and concentrated precipitation they can trigger. Given their high velocity and variability, their prediction is challenging, though it is crucial to issue reliable alarms. The paper presents a neural network approach to forecast the convective cell trajectory...

Air pollution poses a significant threat to human health and ecosystems. Forecasting the concentration of key pollutants like particulate matter can help support air quality planning and prevention measures. Deep learning methods are becoming increasingly popular for predicting air pollution and particulate matter concentration. Architectures like...

The pervasive diffusion of information and communication technologies that has characterized the end of the 20th and the beginning of the 21st centuries has profoundly impacted the way water management issues are studied. The possibility of collecting and storing large data sets has allowed the development of new classes of models that try to infer...

Agriculture is a vital component of human civilization, providing food, fiber, and fuel for billions of people worldwide. However, the agricultural sector has also been identified as a significant contributor to air pollution. This study investigates and analyses the impact of agrofarming activities on air pollution in very productive areas such as...

Most environmental variables, including air pollution, are characterized by high variability in time and space. The classical approach to modelling these variables is developing physically based models with high data and computational requirements or their surrogate version, often implemented through a neural structure. We suggest that adding the g...

Many environmental variables, in particular, related to air or water quality, are measured in a limited number of points and often for a limited time span. This forbids the development of accurate models for those locations due to an insufficient number of data and poses the question of whether a model developed for another measurement station can...

COVID-19 (Coronavirus disease 2019) hit Europe in January 2020. By March, Europe was the active centre of the pandemic. As a result, widespread "lockdown" measures were enforced across the various European countries, even if to a different extent. Such actions caused a dramatic reduction, especially in road traffic. This event can be considered the...

Accurate flow forecasting may support responsible institutions in managing river systems and limiting damages due to high water levels. Machine-learning models are known to describe many nonlinear hydrological phenomena, but up to now, they have mainly provided a single future value with a fixed information structure. This study trains and tests mu...

An integrated modelling approach is used in this work to assess the differences in defining air quality policies in spatial domains of different extensions. The tools used, SHERPA and RIAT+, are public domain and allow to rapidly define the emission scenario of the European area under examination and to solve a multi-objective problem to trade-off...

Two alternative air quality policies are compared: one is the application of only mandatory abatement measures from 2020 to 2030. The second is the definition of a more active and locally-based policy that will lead to a better air quality at the end of the decade. Using an integrated modelling system, we demonstrate that the active policy is quite...

Recurrent neural networks have recently proved the state-of-the-art approach in forecasting complex oscillatory time series on a multi-step horizon. Researchers in the field investigated different machine learning techniques and training approaches on dynamical systems with different degrees of complexity. Still, these analyses are usually limited...

The results of the application of deep neural predictors depend on a multitude of factors which compose the experimental settings. We report all the specific information to ensure the reproducibility of a wide number of numerical experiments. A sensitivity analysis on some critical aspects is provided in order to prove the robustness of our setting...

The problem of forecasting a time series with a neural network is well-defined when considering a single step-ahead prediction. The situation becomes more tangled in the prediction on a multiple-step horizon and consequently the task can be framed in different ways. For example, one can develop a single-step predictor to be used recursively along t...

In this book, we compared different neural approaches in the forecasting of chaotic dynamics, which are well-known for their complex behaviors and the difficulty of their prediction. Our analysis shows that the LSTM predictor trained without teacher forcing is the most accurate approach in the forecasting of complex oscillatory time series. This pr...

Chaotic dynamics are the paradigm of complex and unpredictable evolution due to their built-in feature of amplifying arbitrarily small perturbations. The forecasting of these dynamics has attracted the attention of many scientists since the discovery of chaos by Lorenz in the 1960s. In the last decades, machine learning techniques have shown a grea...

We introduce the basic concepts and methods to formalize and analyze deterministic chaos, with links to fractal geometry. A chaotic dynamic is produced by several kinds of deterministic nonlinear systems. We introduce the class of discrete-time autonomous systems so that an output time series can directly represent data measurements in a real syste...

Four archetypal chaotic maps are used to generate the noise-free synthetic datasets for the forecasting task: the logistic and the Hénon maps, which are the prototypes of chaos in non-reversible and reversible systems, respectively, and two generalized Hénon maps, which represent cases of low- and high-dimensional hyperchaos. We also present a modi...

We examine the performance of different predictors in the deterministic environment and test their robustness against noise. In particular, we mimic the classical case of measurement noise by adding a random Gaussian signal of different intensity to the deterministic output of some archetypal chaotic systems. Then, we examine the critical case of s...

When developing a sustainability plan in a complex and heavily urbanized territory, one of the most relevant options available is installing rooftop photovoltaic (PV) panels. Thus, it is essential to determine the amount of available surface and the potential impact of such installations on the energy and emission budget of the area. Instead of pro...

Recent advances in nonlinear time-series prediction demonstrated the ability of recurrent neural network to forecast chaotic time series on a multi-step horizon, outperforming previous approaches. Researches considered chaotic systems with different degree of complexity, but the analysis was mainly limited to the noise-free case. In this work, we e...

Today, many complex multiobjective problems are dealt with using genetic algorithms (GAs). They apply the evolution mechanism of a natural population to a "numerical" population of solutions to optimize a fitness function. GA implementations must find a compromise between the breath of the search (to avoid being trapped into local minima) and its d...

In the last decades, the great availability of data and computing power drove the development of powerful machine learning techniques in many research areas, including the ones, as the meteorology, where traditional conceptual models were usually adopted. In this work, we analyze the performance obtained by different techniques in the forecasting o...

Today, many complex multi-objective environmental problems are dealt with using genetic algorithms (GAs). They apply the development and adaptation mechanism of a natural population to a "numerical" population of solutions to optimize a fitness function. Such mechanisms, namely: selection, mutation, and cross-over, are all based on a form of random...

The problem of forecasting hourly solar irradiance over a multi-step horizon is dealt with by using three kinds of predictor structures. Two approaches are introduced: Multi-Model (MM) and Multi-Output (MO). Model parameters are identified for two kinds of neural networks, namely the traditional feed-forward (FF) and a class of recurrent networks,...

Most of the building stock in Europe and, in particular, in Lombardy, North of Italy, were built without sufficient attention to energy efficiency. It must be restructured to spare energy, fuel costs, and emissions of traditional pollutants and GHGs. The paper defines an optimization problem that determines the most cost-effective interventions and...

Real-world time series often present missing values due to sensor malfunctions or human errors. Traditionally, missing values are simply omitted or reconstructed through imputation or interpolation methods. Omitting missing values may cause temporal discontinuity. Reconstruction methods, on the other hand, alter in some way the original time series...

With the increasing pressure on water resources availability and dependability and the constraints due to environmental concerns, the traditional approaches for the definition of reservoir management rules turn out to be often inadequate. In particular, in multi-reservoir systems, when several input variables (e.g., the storage of other reservoirs...

In the last few years, many studies claimed that machine learning tools would soon overperform the classical conceptual models in extreme rainfall events forecasting. In order to better investigate this statement, we implement advanced deep learning predictors, such as the deep neural nets, for the forecasting of the occurrence of extreme rainfalls...

The energy consumption of residential buildings represents a relevant portion of energy use at the global level. In some regions of old Europe, a large portion of the residential building stock was built in an era of low energy prices, without much attention to energy efficiency, local pollution, and greenhouse gases emissions. Today they can be re...

Air quality plans must be demonstrated to be economically sustainable and environmentally effective. This paper presents a full cost–benefit and environmental analysis of a large regional air quality plan involving several different actions covering a large spectrum of fields, from domestic heating to passenger and freight transport, from electrici...

Residential buildings represent a considerable portion of the energy demand of a temperate country. Old European regions, where most of the buildings were often built in periods of low energy prices, have a large margin for improvement. The study shows how energy saving measures can be optimally planned at regional level, taking into account the sp...

Comprehensive approaches integrating ecological and socioeconomic objectives are fundamental pillars in the design of more sustainable agroecosystems. To this purpose, we formulated an optimization model aimed to support decisions behind the planning of agricultural ecosystems. We demonstrate the proposed approach onto the design agroecosystems aim...

Multi-reservoir systems management is complex because of the uncertainty on future events and the variety of purposes, usually conflicting, of the involved actors. An efficient management of these systems can help improving resource allocation, preventing political crisis and reducing the conflicts between the stakeholders. Bellman stochastic dynam...

To comply with EU regulations, local environmental authorities of the regions where the mandatory air quality limits are not met must develop suitable emission reduction plans. These normally represent a compromise among what is economically feasible, what is politically acceptable, and what can provide measurable benefits. As a consequence, they i...

“Air quality plans” according to Air Quality Directive 2008/50/EC Art. 23 are the strategic element to be developed, with the aim to reliably meet ambient air quality standards in a cost-effective way. This chapter provides a general framework to develop and assess such plans along the lines of the European Commission’s basic ideas to implement eff...

This chapter provides a review, derived from the extended survey conducted within the APPRAISAL project, of the integrated assessment methodologies used in different countries to design air quality plans and to estimate the effects of emission abatement policy options on human health.

Despite a general improvement expected for the next decade in EU, some urban areas and some regions will still struggle with severe air quality problems and related health effects. These areas are often characterized by specific environmental and anthropogenic factors and will require ad hoc additional local actions to complement medium and long-te...

As already noted, the 2008 European Air Quality Directive (AQD) (2008/50/EC) encourages the use of models in combination with monitoring in a range of applications. It also requires Member States (MS) to design appropriate air quality plans for zones where air quality does not comply with the AQD limit values and to assess possible emission reducti...

The last “Air quality in Europe” report by the European Environmental Agency (EEA 2015) foresees almost five millions of years of life lost (YOLL) in the 28 EU Member States due to the high concentrations of PM2.5. YOLLs are an estimate of the average years that a person would have lived if he or she had not died prematurely, giving greater weight...

To evaluate in practice how IAM can be used to formulate and improve current air quality plans, this chapter reports on the application of one of the existing IAM tools, to two test cases: one for the Brussels Capital Region in Belgium and the other to the region of Porto in the North of Portugal. The two cases are representative for the two option...

The positive health effects of systematic cycling are weighted against the negative effects due to higher pollutant inhalation in the actual case of the city of Milan in northern Italy. The paper first evaluates the actual use of bikes in the city, and then considers why and how much such an active mobility style can be expanded. Two models are use...

“Air quality plans” according to Air Quality Directive 2008/50/EC Art. 23 are the strategic element to be developed, with the aim to reliably meet ambient air quality standards in a cost-effective way. This chapter provides a general framework to develop and assess such plans along the lines of the European Commission’s basic ideas to implement eff...

This chapter provides a review, derived from the extended survey conducted within the APPRAISAL project, of the integrated assessment methodologies used in different countries to design air quality plans and to estimate the effects of emission abatement policy options on human health. The final purpose of this review is to foster the dissemination...

Traditional agroecosystems, aimed at maximizing the short term productivity, are characterized by oversimplification of ecological structure and dependence on the use of external inputs. Moreover, intensive agriculture is one of the main cause of deforestation. The main consequence of traditional agriculture is the loss of natural ecosystems and of...

In recent years, evaluating the robustness of environmental models results has become essential in order to effectively support decision makers to define suitable emission control strategies. This evaluation is performed in literature through uncertainty and sensitivity analyses. Therefore, the application of such methodologies to air quality Integ...

In some European regions, particularly in mountainous areas, the demand for energy is evolving due to the decrease of resident population and the adoption of energy efficiency measures. Such changes are rapid enough to significantly impact on the planning process of wood-to-energy chains that are supposed to work for the following 20–25 years. The...

This paper deals with the clustering of daily wind speed time series based on two features, namelythe daily average wind speed and the corresponding degree of fluctuation. Daily values of the feature pairs are first classified by means of the fuzzy c-means unsupervised clustering algorithm and then results are used to train a supervised MLP neural...

The problem of defining efficient and environmentally compatible short-term agricultural plans for biodiesel exploitation is dealt with in this paper with a multi-objective modelling framework. To optimally use local resources, the first phase of the plan consists in the analysis of land and climate features in order to evaluate which energy crop c...

This paper describes some evidence of fractal order features in wind speed time series recorded at different observation stations both in USA and in Italy. Analysis were performed by using mono-fractal, multi-fractal and power spectra approaches. Results show that the average value of the box dimension for daily and hourly mean wind speed is D = 1....

Crop productivity is commonly assumed as a deterministic function when developing agricultural plans. Actual data prove however that, even for the same soil at the same location, crop productivity can be better interpreted as a random variable due to the meteorological conditions of the specific year. For the production of biodiesel, crops are easi...

When adopting regional plans aimed at improving air quality, environmental authorities are often confronted with the relevant costs that the adoption of abatement measures implies. On the other hand, scientific literature has well documented damages due to air pollution impact on human and ecosystem health. The paper proposes a tool that allows bal...

Biomass from the forest sector can be an important source of renewable energy and can contribute to climate change mitigation and bioenergy development. However, the removal of biomass from forests has significant impacts on the forest ecosystem. For instance, it modifies soil litter which is particularly important to preserve soil characteristics...

Animal wastes from high-density farming have severe impacts on the nitrogen cycle. According to current regulations, the disposal of manure on cropland is constrained by nitrogen content in the agricultural soils. On the contrary, anaerobic digestion (AD) of these wastes can produce energy and a digestate, which is easier to handle than manure and...

In order to use environmental models effectively for management and decision-making, it is vital to establish an appropriate level of confidence in their performance. This paper reviews techniques available across various fields for characterising the performance of environmental models with focus on numerical, graphical and qualitative methods. Ge...

Biomass as a renewable energy source is scarce and its exploitation must be accurately planned in order to maximize the energy produced, the GHG emissions avoided, and the sustainability of other ecological services. By-products and residues are one of the best sources of biomass since they are readily available at no or at a very low cost. Moreove...

The recent statements of both the European Union and the US Presidency pushed in the direction of using renewable forms of energy, in order to act against climate changes induced by the growing concentration of carbon dioxide in the atmosphere. In this paper, a survey regarding methods and tools presently available to determine potential and exploi...

Secondary pollutants (such as PM10) derives from complex non-linear reactions involving precursor emissions, namely VOC, NOx, NH3, primary PM and SO2. Due to difficulty to cope with this complexity, Decision Support Systems (DSSs) are essential tools to help Environmental Authorities to plan air quality policies that fulfill EU Directive 2008/50 re...

The aim of the paper is to propose a method to maximize energy production from arboreous and herbaceous dedicated crops given the characteristics of the local environment: geo-morphology, climate, natural heritage, current land use. The best energy crops available in the Italian panorama are identified and the problem of maximizing the bioenergy pr...

A thorough analysis of biomass supply and of energy demand should be carried out at local scale in order to optimize bioenergy plans and deal with the related social ad environmental issues. We present a method to identify the optimal use of biomass: local biomass availability is assessed, the road network is used to evaluate transportation costs,...

Export Date: 23 October 2012, Source: Scopus

The waste intermodal station of Clyde, in the city of Sydney, Australia, is in the heart of a complex network of terminals connected by road and rail to transport urban waste from its first collection to its final disposal. The amount of waste the network is projected to handle in 2015 will increase from about 340,000 tonnes/year in 2006 up to abou...

Detecting trends on the use of Information and Communication Technologies (ICT) in the domain of environmental sciences is important to foresee new frontiers of modelling and software research. Here we analyze the impact of ICT in scientific papers published from 1990 to 2007 in all ISI journals and in those belonging to the Environmental Sciences...

A holistic model embeds water resources and economic components into a consistent mathematical programming model, with the objective of maximizing economic profits from water uses in various sectors. Such a model can be used to address combined environmental-economic ...

Cited By (since 1996): 2, Export Date: 23 October 2012, Source: Scopus

Growing arboreous and herbaceous species for energetic conversion allows to reduce fossil fuel consumption and greenhouse gases emissions. Moreover, new energetic crops can provide an innovative source of income for agriculture, a sector highly sustained by subsidies in Italy and in the EU. In this paper we propose a methodology to assess energetic...

We use a local learning algorithm to predict the abundance of the Alpine ibex population living in the Gran Paradiso National Park, Northern Italy. Population abundance, recorded for a period of 40 years, have been recently analyzed by [Jacobson, A., Provenzale, A., Von Hardenberg, A., Bassano, B., Festa-Bianchet, M., 2004. Climate forcing and dens...

Models are increasingly being relied upon to inform and support natural resource management. They are incorporating an ever broader range of disciplines and now often confront people without strong quantitative or model-building backgrounds. These trends ...

Public participation to environmental planning and management decisions, as suggested by local Agenda 21 processes, can be supported by software tools developed with a cyclic interaction with all the stakeholders and simple enough to be quickly operated by a large set of heterogeneous users. This also helps preventing their rapid aging and their ex...

Over the last decade, neural network-based flood forecast systems have been increasingly used in hydrological research. Usually, input data of the network are composed by past measurements of flows and rainfalls, without providing a description of the saturation state of the basin, which, in contrast, plays a key role in the rainfall-runoff process...

Given the lack of reliable data on wood combustion for residential heating in Lombardy (Italy), a specific survey has been undertaken: 98.061 questionnaires have been sent by mail to students of 386 secondary schools; 32.993 students (33,6%) of 236 schools filled the questionnaires. Data concerning quantity and quality of wood use, type of combusti...

We propose the application of pruning in the design of neural networks for hydrological prediction. The basic idea of pruning algorithms, which have not been used in water resources problems yet, is to start from a network which is larger than necessary, and then remove the parameters that are less influential one at a time, designing a much more p...

In questo articolo si propone una metodologia per svolgere un accurato bilancio energetico, emissivo ed economico al fine di valutare la convenienza dell'utilizzo delle biomasse come fonte rinnovabile di energia per un territorio a scala provinciale. Sono considerati i costi di raccolta, trasporto e acquisto di sottoprodotti agricoli, forestali e d...

Over the last decade, neural networks-based flood forecast systems have been increasingly used in hydrological studies. Usually, input data of the network are composed by past measurements of flows and rainfalls, without providing a description of the saturation state of the basin, which in contrast plays a key role in the rainfall-runoff process....

PM10 constitutes a major concern for Milan air quality. We presents a series of results obtained applying different neural networks approaches to the PM10 prediction problem. The 1-day ahead prediction shows a satisfactory level of accuracy, which may be further improved if a proper deseasonalization approach is adopted, thus transferring some a pr...

To develop sound air quality plans, regional authorities should have instruments that link the complex behaviour of pollutants both in time and space with costs of emission reduction. The problem is particularly important for ground level ozone which forms kilometres away, hours later from the emission of its precursors. To approach this problem, a...

Designing neural networks predictors by pruning instead of trial and errors significantly reduces the amount of guesswork required to select the optimal architecture. Furthermore, the obtained model is partially connected and hence very parsimonious in the number of parameters, leading to relevant operational advantages in the hydrological forecast...

Ground level ozone pollution is a complex phenomenon heavily affecting industrialized and pop-ulated areas. Ozone is produced by a series of photochemical reactions, activated by the emissions of nitro-gen oxides and volatile organic compounds and may reach maximum concentrations at kilometers of distance form the precursors sources, depending on t...

The optimal flow allocation in the Zambezi system, the largest multi-reservoir water resources system in southern Africa, is analysed. The problem is formulated in network terms and solved with a network flow algorithm. The present configuration of the system is taken as the reference to evaluate the benefits of the proposed modifications to the ex...