Search

Surface cooling from small-to-moderate volcanic eruptions in recent decades has been shown to be important when they occur clustered. In this study, based on newhigh-resolution ice-core data from Greenland, we produce a new volcanic forcing dataset that includes several small-to-moderate eruptions not included in prior reconstructions of the early 19th century and investigate their climate impacts through ensemble simulations with the Max Planck Institute Earth System Model. We find that the clustered small-to-moderate eruptions can additionally produce significant global surface cooling (~0.07 K) during the period 1812-1820, superposing with the cooling by large eruptions in 1809 (unidentified) and 1815 (Tambora). A delayed northward propagation to the higher latitudes is found in the additional surface cooling from small eruptions, but such cooling propagation cannot be confirmed by temperature reconstructions from individual regions due to a low signal-to-noise ratio, hence substantial uncertainties remain for the early 19th-century regional climate anomalies.

Accurately interpreting past climate variability can be a challenging task, particularly when it comes to distinguishing between forced and unforced changes. In the case of large volcanic eruptions, ice core records are a very valuable tool but still often not sufficient to link reconstructed anomaly patterns to a volcanic eruption at all or to its geographical location. In this study, we developed a convolutional neural network (CNN) that is able to classify whether a volcanic eruption occurred and its location (northern hemisphere extratropical, southern hemisphere extratropical, or tropics) with an accuracy of 92%.To train the CNN, we used 100 member ensembles of the MPI-ESM-LR global climate model, generated using the easy volcanic aerosol (EVA) model, which provides the radiative forcing of idealized volcanic eruptions of different strengths and locations. The model considered global sea surface temperature and precipitation patterns 12 months after the eruption over a time period of 3 months.In addition to demonstrating the high accuracy of the CNN, we also applied layer-wise relevance propagation (LRP) to the model to understand its decision-making process and identify the input data that influenced its predictions. Our study demonstrates the potential of using CNNs and interpretability techniques for identifying and locating past volcanic eruptions as well as improving the accuracy and understanding of volcanic climate signals.

Large explosive volcanic eruptions are a potential source of uncertainty in future climate projections as they cannot be predicted in advance, but eventually will occur, causing short-term climatic impacts on both local and global scale. Still, an open topic is the volcanic impact on tropical climate variability, in particular El Niño Southern Oscillation (ENSO) and tropical precipitation and the combined effect of both. Sufficient large ensembles simulations with the same model and radiative forcing scenario but varying initial conditions have become a great tool in recent years to disentangle forced and internal variability). Here we use the EVA-ENS ensemble (Azoulay et al., 2021) which consists of 100-member ensembles of the MPI-ESM-LR for idealized equatorial Pinatubo-like eruptions of different eruption strength and an additional 100-member ensemble without forcing. We are in particular interested if there is a linear volcanic signal on tropical precipitation dependent on the eruption strength and when did it emerge from tropical internal variability.Our results show that for Idealized tropical eruptions global and large hemispheric mean 2m temperature and precipitation anomalies seemed to be scalable with the sulfur emission strength above a certain threshold, except for tropical temperatures for an emission strength > 40 Tg sulfur (S). 10 Tg S emission, the upper estimate of the 1991 Pinatubo eruption, seems to be a threshold where the signal is discernible from internal variability. We also find that seasonal and ensemble mean pattern correlation of 2m temperature and precipitation anomalies are highly correlated in particular for larger emission strengths in the tropics and strongly modulated by ENSO. There is an increasing tendency for a warm ENSO increases with eruption strength. Emergence of the volcanic signal appears for smaller eruption strength when looking to ENSO composites. Emergence of cooling appears on a hemispheric scale, while precipitation response is more localized and mainly confined to the tropics and subtropics. References:Azoulay, A., Schmidt, H., and Timmreck, C.: The Arctic polar vortex response to volcanic forcing of different strengths, J. Geophys. Res., 126, e2020JD034450, doi.org/10.1029/2020JD034450, 2021.

El Niño-Southern Oscillation (ENSO) is one of the major climate phenomena impacting the globe. When a volcanic eruption happens, how ENSO will respond has still no consensus in proxy data though climate models tend to have an El Niño tendency. In this study, using 100 members of diverse (in locations and magnitude) idealized volcanic forcing ensembles, we found that the ENSO responses to north and south extra-tropical eruptions are related to the energy transport to the cooling hemisphere and involve direct and indirect responses through atmospheric and oceanic transport. The north extratropical forcing leads to more El Niño up to three years after eruptions, which is related to the direct atmospheric responses of the southward movement of ITCZ for transporting more energy to the north. The indirect oceanic transport then takes over afterward, leading to more La Niña due to more upwelling in the equatorial eastern Pacific. The south extra-tropical eruptions have less El Niño tendency due to the northward replacement of ITCZ. As the indirect oceanic transport also results in equatorial mean state changes, which may lead to distinct ENSO responses. The long-term ENSO responses from extra-tropical cooling will also be investigated through the simulations from the Extratropical-Tropical Interaction Model Intercomparison Project (ETIN-MIP) experiment.

International audience; A vivid scientific debate exists on the nature of the Atlantic Multidecadal Variability (AMV) as an intrinsic rather than predominantly forced climatic phenomenon, and on the role of ocean circulation. Here, we use a multi-millennial unperturbed control simulation and a Holocene simulation with slow-varying greenhouse gas and orbital forcing performed with the low-resolution version of the Max Planck Institute Earth System Model to illustrate thermohaline conditions associated with twelve events of strong AMV that are comparable, in the surface anomalies, to observations in their amplitudes (~ 0.3 °C) and periods (~ 80 years). The events are associated with recurrent yet spatially diverse same-sign anomalous sea-surface temperature and salinity fields that are substantially symmetric in the warm-to-cold and following cold-to-warm transitions and only partly superpose with the long-term spatial AMV pattern. Subpolar cold-fresh anomalies develop in the deep layers during the peak cold phase of strong AMV events, often in association with subtropical warm-salty anomalies yielding a meridional dipole pattern. The Atlantic meridional overturning circulation (AMOC) robustly weakens during the warm-to-cold transition of a strong AMV event and recovers thereafter, with surface salinity anomalies being potential precursors of such overturning changes. A Holocene simulation with the same model including volcanic forcing can disrupt the intrinsic AMV–AMOC connection as post-eruption periods often feature an AMOC strengthening forced by the volcanically induced surface cooling. Overall, our results support the AMV as a potential intrinsic feature of climate, whose episodic strong anomalous events can display different shades of spatial patterns and timings for the warm-to-cold and subsequent cold-to-warm transitions. Attribution of historical AMV fluctuations thus requires full consideration of the associated surface and subsurface thermohaline conditions and assessing the AMOC–AMV relation.

El Niños are known to decay more rapidly, while La Niñas tend to decay more slowly. Observational analyses and coupled model experiments are conducted to show that sea surface temperature (SST) anomalies over the subtropical northeastern Pacific (SNEP) and equatorial western Pacific (EWP) are key factors to determine the decay pace of the El Niño and La Niña and their asymmetry. In the present climate the La Niña produce larger cold SST anomalies over the regions than the warm SST anomalies produced by the El Niño. The magnitude difference over the SNEP and EWP help to slow down the La Niña decay via subtropical footprinting and tropical thermocline variation mechanisms, respectively. CMIP6 models project the magnitude differences of SNEP SST anomalies between El Niño and La Niña to reduce in the future warming world, causing the asymmetric El Niño-La Niña decay to weaken.

The early 19th century was the coldest period over the past 500 years, when strong tropical volcanic events and a solar minimum coincided. The 1809 unidentified eruption and the 1815 Tambora eruption happened consecutively during the Dalton minimum of solar irradiance; however, the relative role of the two forcing (volcano and solar) agents is still unclear. In this study, we examine the responses from a set of early 19th century simulations with combined and separated volcanic and solar forcing agents, as suggested in the protocol for the past1000 experiment of the Paleoclimate Modelling Intercomparison Project - Phase 4 (PMIP4). From 20-member ensemble simulations with the Max Planck Institute Earth System Model (MPI-ESM1.2-LR), we find that the volcano- and solar-induced surface cooling is additive in the global mean/large scale, regardless of combining or separating the forcing agents. The two solar reconstructions (SATIRE and PMOD) contribute to a cooling before and after 1815 of ~0.05 K and ~0.15 K monthly average near-surface air cooling, respectively, indicating a limited solar contribution to the early 19th century cold period. The volcanic events provide the main cooling contributions, inducing a surface cooling that peaks at ~0.82 K for the 1809 event and ~1.35 K for Tambora. After the Tambora eruption, the temperature in most regions increases toward climatology largely within 5 years, along with the reduction of volcanic forcing. In the northern extratropical oceans, the temperature increases slowly at a constant rate until 1830, which is related to the reduction of seasonality and the concurrent changes in Arctic sea-ice extent. The albedo feedback of Arctic sea ice is found to be the main contributor to the Arctic amplification of the cooling signal. Several non-additive responses to solar and volcanic forcing happen on regional scales. In the atmosphere, the stratospheric polar vortex tends to strengthen when combining both volcano and solar forcing, even though the two forcing agents separately induce opposite-sign changes in stratospheric temperatures and zonal winds. In the ocean, when combining the two forcings, additional surface cold water propagates to the northern extra-tropics from the additional solar cooling in the tropics, which results in regional cooling along the propagation. Overall, this study not only quantifies the surface responses from combinations of the volcano and solar forcing, but also highlights the components that cannot be simply added from the responses of the individual forcing agents, indicating that a relatively small forcing agent (such as solar in early 19th century) can impact the response from the large forcing (such as the 1815 Tambora eruption) when considering regional climates.

This study examines a climate model hindcast of the responses of the western Pacific subtropical high (WPSH) to three types of El Nino events: the Eastern Pacific (EP) El Nino and the types I and II of Central Pacific (CP-I and CP-II) El Nino. These El Nino types differ from each other in the central locations and patterns of their sea surface temperature (SST) anomalies. They invoke four different mechanisms to impact the WPSH. Hindcasts produced by the Taiwan Central Weather Bureau (CWB) Climate Forecast System 1-tiered model (TCWB1T1) are analyzed. These hindcasts realistically simulate the impacts on the WPSH during the CP-I El Nino, but overestimate the impacts during the decaying summer of the EP El Nino and during the developing autumn and early winter of the CP-II El Nino. The overestimates are mainly the result of an overly strong Maritime Continent regional circulation mechanism during EP El Ninos and an overly strong Indian Ocean capacitor mechanism during CP-II El Ninos. Further analyses show that these model biases are related to biases in the simulations of El Nino SST anomalies and the Walker circulation. Both model deficiencies are common to contemporary coupled climate models.

This study compares the impacts of the El Niño–Southern Oscillation (ENSO) on sea surface temperatures (SSTs) in the tropical North Atlantic Ocean and the tropical Indian Ocean during 1958–2004. It is found that the tropical atmospheric processes mediating the ENSO impacts are different between the two oceans for two reasons. First, the ENSO-induced anomalous Walker circulation is more extensive over the Atlantic than over the Indian Ocean. As a result, the atmospheric bridge (AB) mechanism is the major contributor to the differences in ENSO teleconnections between the two oceans. Secondly, SSTs in the tropical North Atlantic are under a greater control of the atmospheric thermal forcing than those in the tropical Indian Ocean. Due to these different controls, the tropospheric temperature (TT) mechanism also contributes to the different ENSO teleconnections. When compared with the observations, the mean of thirty-seven models from the Coupled Model Intercomparison Project Phase 5 overestimates the ENSO-induced SST response in the tropical Indian Ocean but underestimates the response in the tropical North Atlantic. The overestimation is brought about by a westward extension of ENSO SST anomalies in the models, which causes the AB mechanism to produce an overly strong impact on Indian Ocean SSTs. On the other hand, the underestimation is caused by a weaker-than-observed sensitivity in the simulated Atlantic SSTs to the thermal forcing produced by the TT mechanism.

The Atlantic Multidecadal Variability (AMV) modulates the North Atlantic surface ocean variability and affects decadal climate evolution up to the global scale; however, the underlying mechanisms of the AMV remains debated. We use a multi-model ensemble of transient past-millennium and unperturbed preindustrial control simulations contributing to the Paleoclimate Modelling Intercomparison Project - Phase 4 (PMIP4) to decompose the AMV signal into its internal and external components. The internal component of AMV exhibits no robust behavior across simulations during periods of major forcing such as strong volcanic eruptions, whereas the externally-forced component of AMV responds to volcanic eruptions with an immediate radiative cooling followed, in some simulations, by a sequence of damped multidecadal oscillations. This indicates that the intrinsic mechanism underlying the AMV is distinguishable from its response to external forcing. The internal component of AMV is tightly connected with the Atlantic meridional overturning circulation (AMOC) and controls the variations of AMV. The external component of AMV explains about 25% of the variance in the past millennium simulations, though less-consistency is found between models. Our results further indicate that the spatial imprint of external volcanic forcing on North Atlantic sea-surface temperatures differs from the surface pattern of the internal AMV contributing to the lack of robustness for the AMV pattern.

This paper provides initial results from a multi-model ensemble analysis based on the volc-pinatubo-full experiment performed within the Model Intercomparison Project on the climatic response to Volcanic forcing (VolMIP) as part of the sixth phase of the Coupled Model Intercomparison Project (CMIP6). The volc-pinatubo-full experiment is based on an ensemble of volcanic forcing-only climate simulations with the same volcanic aerosol dataset across the participating models (the 1991–1993 Pinatubo period from the CMIP6-GloSSAC dataset). The simulations are conducted within an idealized experimental design where initial states are sampled consistently across models from the CMIP6-piControl simulation providing unperturbed preindustrial background conditions. The multi-model ensemble includes output from an initial set of six participating Earth system models (CanESM5, GISS-E2.1-G, IPSL-CM6A-LR, MIROC-E2SL, MPI-ESM1.2-LR and UKESM1). The results show overall good agreement between the different models on the global and hemispheric scales concerning the surface climate responses, thus demonstrating the overall effectiveness of VolMIP's experimental design. However, small yet significant inter-model discrepancies are found in radiative fluxes, especially in the tropics, that preliminary analyses link with minor differences in forcing implementation; model physics, notably aerosol–radiation interactions; the simulation and sampling of El Niño–Southern Oscillation (ENSO); and, possibly, the simulation of climate feedbacks operating in the tropics. We discuss the volc-pinatubo-full protocol and highlight the advantages of volcanic forcing experiments defined within a carefully designed protocol with respect to emerging modelling approaches based on large ensemble transient simulations. We identify how the VolMIP strategy could be improved in future phases of the initiative to ensure a cleaner sampling protocol with greater focus on the evolving state of ENSO in the pre-eruption period.

The early 19th century was the coldest period over the past 500 years, when strong tropical volcanic events and a solar minimum coincided. The 1809 unidentified eruption and the 1815 Tambora eruption happened consecutively during the Dalton minimum of solar irradiance; however, the relative role of the two forcing (volcano and solar) agents is still unclear. In this study, we examine the responses from a set of early 19th century simulations with combined and separated volcanic and solar forcing agents, as suggested in the protocol for the past1000 experiment of the Paleoclimate Modelling Intercomparison Project – Phase 4 (PMIP4). From 20-member ensemble simulations with the Max Planck Institute Earth system model (MPI-ESM1.2-LR), we find that the volcano- and solar-induced surface cooling is additive in the global mean/large scale, regardless of combining or separating the forcing agents. The two solar reconstructions (SATIRE (Spectral and Total Irradiance REconstruction-Millennia model) and PMOD (Physikalisch-Meteorologisches Observatorium Davos)) contribute to a cooling before and after 1815 of ∼0.05 and ∼0.15 K monthly average near-surface air cooling, respectively, indicating a limited solar contribution to the early 19th century cold period. The volcanic events provide the main cooling contributions, inducing a surface cooling that peaks at ∼0.82 K for the 1809 event and ∼1.35 K for Tambora. After the Tambora eruption, the temperature in most regions increases toward climatology largely within 5 years, along with the reduction of volcanic forcing. In the northern extratropical oceans, the temperature increases slowly at a constant rate until 1830, which is related to the reduction of seasonality and the concurrent changes in Arctic sea-ice extent. The albedo feedback of Arctic sea ice is found to be the main contributor to the Arctic amplification of the cooling signal. Several non-additive responses to solar and volcanic forcing happen on regional scales. In the atmosphere, the stratospheric polar vortex tends to strengthen when combining both volcano and solar forcing, even though the two forcing agents separately induce opposite-sign changes in stratospheric temperatures and zonal winds. In the ocean, when combining the two forcings, additional surface cold water propagates to the northern extratropics from the additional solar cooling in the tropics, which results in regional cooling along the propagation. Overall, this study not only quantifies the surface responses from combinations of the volcano and solar forcing, but also highlights the components that cannot be simply added from the responses of the individual forcing agents, indicating that a relatively small forcing agent (such as solar in early 19th century) can impact the response from the large forcing (such as the 1815 Tambora eruption) when considering regional climates.

Volcanic eruptions and reduced solar radiance can individually cool our globe through both direct changes in incoming radiation and indirect influences from dynamical processes. However, whether the cooling from the combination of two forcing can be linearly additive, or if additional cooling exists when reduced solar radiance is imposed during volcanic eruptions remains unclear. In this project, by using the state-of-art climate model (MPI-ESM1-2-LR), we found that the total cooling of the two forcing can be additive, but also have additional cooling during the period when volcanic cooling bouncing back to climatology. Our experiments focus on the early 19th century (1791-1850) since the period existed multiple strong volcanic events (especially the 1809 unidentified eruption and 1815 Tambora eruption), a solar minimum (Dalton minimum from 1790-1830), and limited influence from anthropogenic greenhouse gases. In the presentation, we will discuss how volcanic eruptions and different amplitudes of solar reconstructions can individually and together cool the surface through both direct radiative changes and dynamical influences. Our main focus will be how the atmospheric circulation may influence the polar sea ice and large-scale climate patterns when imposing combinations of solar and volcanic forcing.

Author(s): Yu, Jin-Yi; Fang, Shih-Wei | Abstract: An ENSO event can transition from one event to another in complex ways. An El Nino (La Nina) event can be preceded by a La Nina (El Nina) event to become a cyclic ENSO, by a neutral event to become an episodic ENSO, or by another El Nino (La Nina) event to become a multi-year ENSO. We find that the observed El Nino and La Nina exhibit different complexities in their event-to-event transition patterns. The El Nino is dominated in order by episodic, cyclic, and multi-year transitions, but the reversed order is found in the La Nina. This difference in the transition complexity arises from a subtropical Pacific forcing mechanism that triggers ENSO events. Using observational analyses and forced atmospheric model experiments, we show that a preceding ENSO event can activate a subtropical Pacific forcing mechanism to trigger another ENSO event during the following year. These tropical-subtropical Pacific interactions result in a cyclic ENSO transition if the two ENSO events are of opposite signs or a multi-year ENSO transition if they are of the same sign. The preceding ENSO event should excite deep convections in the tropical Pacific in order to activate the subtropical Pacific mechanism. This requirement enables mean temperatures in the cold tongue and warm pool to respectively control how easily the cyclic and multi-year transitions can occur. This mean state control enables the subtropical Pacific forcing mechanism to result in more multi-year transitions for La Nina than El Nino and more episodic transitions for El Nino than La Nina. Furthermore, a future warmer tropical Pacific is projected to decrease the frequency of occurrence of multi-year ENSO transitions but increase the occurrence of cyclic ENSO transitions.. We find that the CMIP5 and CMIP6 models can reproduce the transition complexity for El Nino but not for La Nina. The models tend to produce too many episodic La Nina events and too few multi-year La Nina events. We are able to link the former deficiency to a weaker than observed subtropical Pacific forcing mechanism in the CMIP5/6 models and the latter to a cold bias in mean state SSTs in the equatorial Pacific in the CMIP5/6 models. To achieve better simulations of ENSO transition complexity, further efforts are to improve the model deficiencies in simulating the SP-onset mechanism and mean SSTs in the equatorial Pacific.

Author(s): Fang, SW; Yu, JY | Abstract: The observed El Nino and La Nina exhibit different complexities in their event-to-event transition patterns. The El Nino is dominated in order by episodic, cyclic, and multiyear transitions, but the reversed order is found in the La Nina. A subtropical Pacific onset mechanism is used to explain this difference. This mechanism triggers El Nino/La Nina events via subtropical processes and is responsible for producing multiyear and episodic transitions. Its nonlinear responses to the tropical Pacific mean state result in more multiyear transitions for La Nina than El Nino and more episodic transitions for El Nino than La Nina. The CMIP5/6 models realistically simulate the observed transition complexity of El Nino but fail to simulate the transition complexity of La Nina. This deficiency in CMIP5 models arises from a weaker than observed subtropical onset mechanism and a cold bias in the tropical Pacific mean sea surface temperatures in the models.

Author(s): He, S; Yu, JY; Yang, S; Fang, SW | Abstract: During 1958–2017, the Central-Pacific (CP) El Nino evolved into La Nina less frequently (38%) than the Eastern-Pacific (EP) El Nino (75%). Composite analyses reveal that the reversal of zonal wind anomalies in the tropical western Pacific is the key mechanism for the EP El Nino's transitions to La Nina. This reversal induces oceanic Kelvin waves to promote the La Nina onset. This reversal mechanism is often triggered by the Indo-Pacific teleconnection produced by the EP El Nino. Consequently, the EP El Nino often experiences the transitional evolution. For the CP events, the southward shift of westerly anomalies in the tropical central Pacific is the key mechanism for transitions from El Nino to La Nina via local processes. However, the subtropical teleconnection of the CP El Nino prevents this mechanism from occurring and often causes the nontransitional evolution for the CP events.

Author(s): Yu, JY; Fang, SW | Abstract: This study finds the seasonal footprinting (SF) mechanism to be a key source of El Nino–Southern Oscillation (ENSO) complexity, whereas the charged-discharged (CD) mechanism acts to reduce complexity. The CD mechanism forces El Nino and La Nina to follow each other, resulting in a more cyclic and less complex ENSO evolution, while the SF mechanism involves subtropical forcing and results in an ENSO evolution that is more episodic and irregular. The SF mechanism also has a tendency to produce multiyear La Nina events but not multiyear El Nino events, contributing to El Nino-La Nina asymmetries. The strength of CD mechanism has been steady, but SF mechanism has intensified during the past two decades, making ENSO more complicated. Most Climate Model Intercomparison Project version 5 models overestimate the strength of the CD mechanism but underestimate the strength of the SF mechanism, causing their simulated ENSOs to be too regular and symmetric.

Code and Data for the Submission to Nature Climate Change with title, "Global warming reduces ENSO complexity".

Think about someone taking control of your car while you're driving. Or, someone hacking into a drone and taking control. Both of these things have been done, and both are attacks against cyber-physical systems (CPS). Securing Cyber-Physical Systems explores the cybersecurity needed for CPS, with a focus on results of research and real-world deployment experiences. It addresses CPS across multiple sectors of industry. CPS emerged from traditional engineered systems in the areas of power and energy, automotive, healthcare, and aerospace. By introducing pervasive communication support in those systems, CPS made the systems more flexible, high-performing, and responsive. In general, these systems are mission-criticaltheir availability and correct operation is essential. This book focuses on the security of such mission-critical systems. Securing Cyber-Physical Systems brings together engineering and IT experts who have been dealing separately with these issues. The contributed chapters in this book cover a broad range of CPS security topics, including: Securing modern electrical power systems Using moving target defense (MTD) techniques to secure CPS Securing wireless sensor networks (WSNs) used for critical infrastructures Mechanisms to improve cybersecurity and privacy in transportation CPS Anticipated cyberattacks and defense approaches for next-generation autonomous vehicles Security issues, vulnerabilities, and challenges in the Internet of Things Machine-to-machine (M2M) communication security Security of industrial control systems Designing "trojan-resilient" integrated circuits While CPS security techniques are constantly evolving, this book captures the latest advancements from many different fields. It should be a valuable resource for both professionals and students working in network, web, computer, or embedded system security.

Online social media such as Facebook has started transforming our lives in the past few years. One of the main user concerns in social media is the privacy of personal information. Although social media provides options to manage privacy, those user settings are often complicated, vague, and not user friendly. In this paper, we propose an automated and simple way to manage Facebook privacy by changing the privacy to three predefined levels: basic, medium, and advanced. For platform independence and wide usability, we discuss the development of the proposed application in two different flavors: a PHP application and Firefox add-on.

We demonstrate the fabrication of the polymer hollow waveguide on a Si substrate by excimer laser direct writing and its characteristics of optical transmission. A hollow waveguide with transmission loss of 0.019 dB/ μm had been achieved at wavelength of 1.55 μm. In addition, the effect of coating material to the characteristics of the transmission of the polymer hollow waveguides was presented.

We study on artificial neural network-based controllers which are either trained or evolved by using the supervised or unsupervised learning approach. We employed backpropagation for the supervised method and the genetic algorithm for the unsupervised method. After training the controllers, we applied the controllers to our three newly designed mini-3D games. We performed a comprehensive study on the performance and weaknesses of the controllers. We emerged the controllers as fundamental tools for giving us more understanding about artificial neural network and its effectiveness in imitating players’ behaviours.