Habitable Zone Research Articles

Christian Huygens and William Derham and 18th Century Precursors to the Habitable Zone

Both Christian Huygens and William Derham expressed ideas that are prescient to the concept of a circumstellar habitable zone: liquid water is a precondition for life, there is a region within the solar system within which liquid surface water can exist upon planets, the stars are suns around which planetary systems should be common, these extrasolar planetary systems may include habitable worlds. Although neither author explicitly developed the phraseology of an exoplanetary habitable zone based upon liquid water, such a concept would follow from their writings.

Closeby Habitable Exoplanet Survey (CHES). II. An Observation Strategy for the Target Stars

The Closeby Habitable Exoplanet Survey (CHES) constitutes a mission intricately designed to systematically survey approximately 100 solar-type stars located within the immediate proximity of the solar system, specifically within a range of 10 pc. The core objective of this mission is the detection and characterization of potentially habitable Earth-like planets or super-Earths within the habitable zone of these stars. The CHES mission obtains high-precision astrometric measurements of planets orbiting the target stars by observing angular distance variations between the target star and reference stars. As a result, we surveyed the relevant parameters of both target and reference stars in detail, conducting a thorough analysis and calculation of the required observation accuracy, the number of observations, and the priority assigned to each target star. Observational emphasis will be concentrated on targets considered of higher priority, ensuring the effectiveness of their observation capabilities. Through this approach, we formulate a 5 yr observation strategy that will cover all the target stars within a 6 month time frame. The strategy not only fulfills the required observing capability but also exhibits high efficiency simultaneously, providing an executable program for future mission. Over the span of the mission’s 5 yr duration, a cumulative observation time of 29,220 hr will be available. Approximately 86% of this, totaling 25,120 hr, is allocated for the observation of target stars. This allocation leaves approximately 4100 hr for extended scientific observation programs. We have also performed simulated observations based on this strategy and verified its observational capability for exoplanets.

Statistics and Habitability of F-type Star–Planet Systems

F-type star–planet systems represent an intriguing case for habitability studies. Although F-type stars spend considerably less time on the main sequence (MS) than G-, K-, and M-type stars, they still offer a unique set of features, allowing for the principal possibility of exolife. Examples of these features include the increased widths of stellar habitable zones as well as the presence of enhanced UV flux, which in moderation may have added to the origin of life in the Universe. In this study, we pursue a detailed statistical analysis of the currently known planet-hosting F-type stars by making use of the NASA Exoplanet Archive. After disregarding systems with little or no information on the planet(s), we identify 206 systems of interest. We also evaluate whether the stars are on the MS based on various criteria. In one approach, we use the stellar evolution code MESA. Depending on the adopted criterion, about 60–80 stars have been identified as MS stars. In 18 systems, the planet spends at least part of its orbit within the stellar habitable zone. In one case, i.e., HD 111998, known as 38 Vir, the planet is situated in the habitable zone at all times. Our work may serve as a basis for future studies, including studies on the existence of Earth-mass planets in F-type systems, as well as investigations of possibly habitable exomoons hosted by exo-Jupiters, as the lowest-mass habitable zone planet currently identified has a mass estimate of 143 Earth masses.

Water Evolution and Inventories of Super-Earths Orbiting Late M Dwarfs

Super-Earths orbiting M dwarf stars may be the most common habitable planets in the Universe. However, their habitability is threatened by intense irradiation from their host stars, which drives the escape of water to space and can lead to surface desiccation. We present simulation results of a box model incorporating deep-water cycling between interior and atmosphere and water loss to space for terrestrial planets of mass 1–8 M ⊕ orbiting in the habitable zone of a late M dwarf. Energy-limited loss decreases with planetary mass, while diffusion-limited loss increases with mass. Depending on where it orbits in the habitable zone, a 1 M ⊕ planet that starts with 3–8 Earth Oceans can end up with an Earthlike surface of oceans and exposed continents; for an 8 M ⊕ super-Earth, that range is 3–12 Earth Oceans. Planets initialized with more water end up as waterworlds with no exposed continents, while planets that start with less water have desiccated surfaces by 5 Gyr. Since the mantles of terrestrial planets can hold much more water than is currently present in Earth’s atmosphere, none of our simulations result in Dune planets—such planets may be less common than previously thought. Further, more water becomes sequestered within the mantle for larger planets. A super-Earth at the inner edge of the habitable zone tends to end up as either a waterworld or with a desiccated surface; only a narrow range of initial water inventory yields an Earthlike surface.

High-resolution Elemental Abundance Measurements of Cool JWST Planet Hosts Using AutoSpecFit: An Application to the Sub-Neptune K2-18b’s Host M Dwarf

We present an in-depth, high-resolution spectroscopic analysis of the M dwarf K2-18, which hosts a sub-Neptune exoplanet in its habitable zone. We show our technique to accurately normalize the observed spectrum, which is crucial for a proper spectral fitting. We also introduce a new automatic, line-by-line, model-fitting code, AutoSpecFit, which performs an iterative χ 2 minimization process to measure individual elemental abundances of cool dwarfs. We apply this code to the star K2-18, and measure the abundance of 10 elements: C, O, Na, Mg, Al, K, Ca, Sc, Ti, and Fe. We find these abundances to be moderately supersolar, except for Fe, with a slightly subsolar abundance. The accuracy of the inferred abundances is limited by the systematic errors due to uncertain stellar parameters. We also derive the abundance ratios associated with several planet-building elements such as Al/Mg, Ca/Mg, Fe/Mg, and (a solar-like) C/O = 0.568 ± 0.026, which can be used to constrain the chemical composition and the formation location of the exoplanet. On the other hand, the planet K2-18 b has attracted considerable interest, given the JWST measurements of its atmospheric composition. Early JWST studies reveal an unusual chemistry for the atmosphere of this planet, which is unlikely to be driven by formation in a disk of unusual composition. The comparison between the chemical abundances of K2-18 b from future JWST analyses and those of the host star can provide fundamental insights into the formation of this planetary system.

Climate Bistability at the Inner Edge of the Habitable Zone due to Runaway Greenhouse and Cloud Feedbacks

Understanding the climate dynamics at the inner edge of the habitable zone is crucial for predicting the habitability of rocky exoplanets. Previous studies using global climate models (GCMs) have indicated that planets receiving high stellar flux can exhibit climate bifurcations, leading to bistability between a cold (temperate) and a hot (runaway) climate. However, the mechanism causing this bistability has not been fully explained, in part due to the difficulty associated with inferring mechanisms from small numbers of expensive numerical simulations in GCMs. In this study, we employ a two-column (dayside and nightside), two-layer climate model to investigate the physical mechanisms driving this bistability. Through mechanism-denial experiments, we demonstrate that the runaway greenhouse effect, coupled with a cloud feedback on either the dayside or nightside, leads to climate bistability. We also map out the parameters that control the location of the bifurcations and size of the bistability. This work identifies which mechanisms and GCM parameters control the stellar flux at which rocky planets are likely to retain a hot, thick atmosphere if they experience a hot start. This is critical for the prioritization of targets and interpretation of observations by the James Webb Space Telescope. Furthermore, our modeling framework can be extended to planets with different condensable species and cloud types.

Climate Regimes across the Habitable Zone: A Comparison of Synchronous Rocky M and K Dwarf Planets

M and K dwarf stars make up 86% of the stellar population and host many promising astronomical targets for detecting habitable climates in the near future. Of the two, M dwarfs currently offer greater observational advantages and are home to many of the most exciting observational discoveries in the last decade. But K dwarfs could offer even better prospects for detecting habitability by combining the advantages of a relatively dim stellar flux with a more stable stellar environment. Here we explore the climate regimes that are possible on Earth-like synchronous planets in M and K dwarf systems, and how they vary across the habitable zone. We focus on surface temperature patterns, water availability, and implications for habitability. We find that the risk of nightside cold trapping decreases with increased orbital radius and is overall lower for K dwarf planets. With reduced atmospheric shortwave absorption, K dwarf planets have higher dayside precipitation rates and less day-to-night moisture transport, resulting in lower nightside snow rates. These results imply a higher likelihood of detecting a planet with a moist dayside climate in a habitable “eyeball” climate regime orbiting a K dwarf star. We also show that “terminator habitability” can occur for both M and K dwarf land planets, but would likely be more prevalent in M dwarf systems. Planets in a terminator habitability regime tend to have slightly lower fractional habitability, but offer alternative advantages including instellation rates more comparable to Earth in regions that have temperatures amenable to life.

Impact of vegetation albedo on the habitability of Earth-like exoplanets

ABSTRACT Vegetation can modify the planetary surface albedo via the Charney mechanism, as plants are usually darker than the bare surface of the continents. We updated ESTM (Earth-like surface temperature model) to incorporate the presence, distribution and evolution of two dynamically competing vegetation types that resemble grasslands and trees (the latter in the double stages of life: adults and seedlings). The newly developed model was applied to estimate how the climate-vegetation system reaches equilibrium across different rocky planetary configurations, and to assess its impact on temperature and habitability. With respect to a world with bare granite continents, the effect of vegetation-albedo feedback is to increase the average surface temperature. Since grasses and trees exhibit different albedos, they affect temperature to different degrees. The ultimate impact on climate depends on the outcome of the competition between these vegetation types. The change in albedo due to vegetation extends the habitable zone and enhances the overall planetary habitability beyond its traditional outer edge. This effect is especially relevant for planets that have a larger extension of continents than Earth. For Earth, the semimajor axis d = 1.04 au represents the turning point where vegetation enhances habitability from h = 0.0 to 0.485 (in the grass-dominance case), to h = 0.584 (in the case of coexistence between grasses and trees), and to h = 0.612 (in the tree-dominance case). This illustrates the transition from a snowball state to a planet with intermediate habitability at the outer edge of the circumstellar habitability zone.

Educational technologies in schools in Northern Ireland: Teachers’ digital competences in the Goldilocks zone

The digital transformation of the educational landscape is an integral part of 21st-century learning, yet not all regions have capitalized on the benefits edtech brings. However, Northern Ireland’s (NI’s) education system presents a uniquely opportune environment for embracing edtech, acting as a veritable Goldilocks zone—where conditions appear just right for educational technology’s successful deployment. This work provides a significant expansion to the range and depth of research into educational technologies in NI and important point of reference for schooling, internationally. Notably, the research reveals an urgent need for a robust teacher competence framework. This framework would focus on developing the digital skills of educators, which would, in turn, enhance their digital capital—the skills, knowledge, and attitudes toward digital technologies that enable meaningful engagement in digital activities. The findings also underscore the critical importance of a strategic vision in the application of digital technology in pedagogy.

Novel Atmospheric Dynamics Shape the Inner Edge of the Habitable Zone around White Dwarfs

White dwarfs offer a unique opportunity to search nearby stellar systems for signs of life, but the habitable zone around these stars is still poorly understood. Since white dwarfs are compact stars with low luminosity, any planets in their habitable zone should be tidally locked, like planets around M dwarfs. Unlike planets around M dwarfs, however, habitable white dwarf planets have to rotate very rapidly, with orbital periods ranging from hours to several days. Here we use the ExoCAM global climate model to investigate the inner edge of the habitable zone around white dwarfs. Our simulations show habitable planets with ultrashort orbital periods (P ≲ 1 day) enter a “bat rotation” regime, which differs from typical atmospheric circulation regimes around M dwarfs. Bat rotators feature mean equatorial subrotation and a displacement of the surface’s hottest regions from the equator toward the midlatitudes. We qualitatively explain the onset of bat rotation using shallow water theory. The resulting circulation shifts increase the dayside cloud cover and decrease the stratospheric water vapor, expanding the white dwarf habitable zone by ∼50% compared to estimates based on 1D models. The James Webb Space Telescope should be able to quickly characterize bat rotators around nearby white dwarfs thanks to their distinct thermal phase curves. Our work underlines that tidally locked planets on ultrashort orbits may exhibit unique atmospheric dynamics, and guides future habitability studies of white dwarf systems.

Too little, too much, and "just right": Exploring the "goldilocks zone" of daily stress reactivity.

Hormetic models of stress resilience describe nonlinear relations for exposure to adversity and health outcomes, where exposure induces salutary changes up to a threshold, with changes becoming deleterious afterward. Here we apply a hormetic model of stress to reactivity to daily stressors, examining whether mental and physical health benefits arise from low-to-moderate reactivity but then decrease at higher levels. Data are from the second wave of the National Study of Daily Experiences (NSDE). Adults (N = 2,022; Mage = 58.61, SD = 12.12, age range: 35-86; 57% female) completed telephone interviews detailing their stressors and affect on eight consecutive evenings. A series of multilevel structural equation models estimated within-person associations between daily stressors and negative affect (i.e., stress reactivity), and between-person linear and quadratic effects of stress reactivity on mental and physical health outcomes (i.e., life satisfaction, psychological distress, and number of chronic conditions). Findings reveal a significant quadratic effect for each outcome, indicating a U-shaped pattern (inverse U for positively valenced life satisfaction), such that low and high levels of stress reactivity were associated with poorer health and well-being, whereas moderate levels of daily stress reactivity predicted better health outcomes. These findings suggest that individuals who display either very low- or very high-stress reactivity may benefit from interventions that target their emotion regulation skills and coping resources. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Climatic Effects of Ocean Salinity on M Dwarf Exoplanets

Ocean salinity is known to dramatically affect the climates of Earth-like planets orbiting Sun-like stars, with high salinity leading to less ice and higher surface temperature. However, how ocean composition impacts climate under different conditions, such as around different types of stars or at different positions within the habitable zone, has not been investigated. We used ROCKE-3D, an ocean-atmosphere general circulation model, to simulate how planetary climate responds to ocean salinities for planets with G-star versus M dwarf hosts at several stellar fluxes. We find that increasing ocean salinity from 20 to 100 g kg−1 in our model results in nonlinear ice reduction and warming on G-star planets, sometimes causing abrupt transitions to different climate states. Conversely, sea ice on M dwarf planets responds more gradually and linearly to increasing salinity. Moreover, reductions in sea ice on M dwarf planets are not accompanied by significant surface warming as on G-star planets. High salinity can modestly bolster the resilience of M dwarf planets against snowball glaciation and allow these planets to retain surface liquid water further from their host star, but the effects are muted compared to G-star planets that experience snowball bifurcation and climate hysteresis due to the ice-albedo feedback.

The Implications of ‘Oumuamua on Panspermia

Panspermia is the hypothesis that life originated on Earth from the bombardment of foreign interstellar ejecta harboring polyextremophile microorganisms. Since the 2017 discovery of the interstellar body ‘Oumuamua (1I/2017 U1) by the Pan-STARRS telescope, various studies have reexamined panspermia based on updated number density models that accommodate for ‘Oumuamua’s properties. By utilizing ‘Oumuamua’s properties as an anchor, we estimate the mass and number density of ejecta in the interstellar medium (ρ m [units of kg au−3] and ρ n [units of au−3]). We build upon prior work by first accounting for the minimum ejecta size to shield microbes from supernova radiation. Second, we estimate the total number of impact events C n on Earth after its formation and prior to the emergence of life (≈0.8 Gyr). We derive a conditional probability relation for the likelihood of panspermia for Earth specifically of <10−5, given a number of factors including f B, the fraction of ejecta harboring extremophiles and other factors that are poorly constrained. However, we find that panspermia is a plausible potential life-seeding mechanism for (optimistically) potentially up to ∼105 of the ∼109 Earth-sized habitable zone worlds in our Galaxy.

How molecular architecture defines quantum yields

Understanding the intricate relationship between molecular architecture and function underpins most challenges at the forefront of chemical innovation. Bond-forming reactions are particularly influenced by the topology of a chemical structure, both on small molecule scale and in larger macromolecular frameworks. Herein, we elucidate the impact that molecular architecture has on the photo-induced cyclisations of a series of monodisperse macromolecules with defined spacers between photodimerisable moieties, and examine the relationship between propensity for intramolecular cyclisation and intermolecular network formation. We demonstrate a goldilocks zone of maximum reactivity between the sterically hindered and entropically limited regimes with a quantum yield of intramolecular cyclisation that is nearly an order of magnitude higher than the lowest value. As a result of the molecular design of trifunctional macromolecules, their quantum yields can be deconvoluted into the formation of two different cyclic isomers, as rationalised with molecular dynamics simulations. Critically, we visualise our solution-based studies with light-based additive manufacturing. We formulate four photoresists for microprinting, revealing that the precise positioning of functional groups is critical for resist performance, with lower intramolecular quantum yields leading to higher-quality printing in most cases.

Functional redundancy of ubiquitin-like sulfur-carrier proteins facilitates flexible, efficient sulfur utilization in the primordial archaeon Thermococcus kodakarensis.

Ubiquitin-like proteins (Ubls) in eukaryotes and bacteria mediate sulfur transfer for the biosynthesis of sulfur-containing biomolecules and form conjugates with specific protein targets to regulate their functions. Here, we investigated the functions and physiological importance of Ubls in a hyperthermophilic archaeon by constructing a series of deletion mutants. We found that the Ubls (TK1065, TK1093, and TK2118) in Thermococcus kodakarensis are conjugated to their specific target proteins, and all three are involved in varying degrees in the biosynthesis of sulfur-containing biomolecules such as tungsten cofactor (Wco) and tRNA thiouridines. TK2118 (named UblB) is involved in the biosynthesis of Wco in a glyceraldehyde 3-phosphate:ferredoxin oxidoreductase, which is required for glycolytic growth, whereas TK1093 (named UblA) plays a key role in the efficient thiolation of tRNAs, which contributes to cellular thermotolerance. Intriguingly, in the presence of elemental sulfur (S0) in the culture medium, defective synthesis of these sulfur-containing molecules in Ubl mutants was restored, indicating that T. kodakarensis can use S0 as an alternative sulfur source without Ubls. Our analysis indicates that the Ubl-mediated sulfur-transfer system in T. kodakarensis is important for efficient sulfur assimilation, especially under low S0 conditions, which may allow this organism to survive in a low sulfur environment.IMPORTANCESulfur is a crucial element in living organisms, occurring in various sulfur-containing biomolecules including iron-sulfur clusters, vitamins, and RNA thionucleosides, as well as the amino acids cysteine and methionine. In archaea, the biosynthesis routes and sulfur donors of sulfur-containing biomolecules are largely unknown. Here, we explored the functions of Ubls in the deep-blanched hyperthermophilic archaeon, Thermococcus kodakarensis. We demonstrated functional redundancy of these proteins in the biosynthesis of tungsten cofactor and tRNA thiouridines and the significance of these sulfur-carrier functions, especially in low sulfur environments. We propose that acquisition of a Ubl sulfur-transfer system, in addition to an ancient inorganic sulfur assimilation pathway, enabled the primordial archaeon to advance into lower-sulfur environments and expand their habitable zone.

Controls of Atmospheric Methane on Early Earth and Inhabited Earth-like Terrestrial Exoplanets

Methane (CH4) is a primarily biogenic greenhouse gas. As such, it represents an essential biosignature to search for life on exoplanets. Atmospheric CH4 abundance on Earth-like inhabited exoplanets is likely controlled by marine biogenic production and atmospheric photochemical consumption. Such interactions have been previously examined for the case of the early Earth where primitive marine ecosystems supplied CH4 to the atmosphere, showing that the atmospheric CH4 response to biogenic CH4 flux variations is nonlinear, a critical property when assessing CH4 reliability as a biosignature. However, the contributions of atmospheric photochemistry, metabolic reactions, or solar irradiance to this nonlinear response are not well understood. Using an atmospheric photochemical model and a marine microbial ecosystem model, we show that the production of hydroxyl radicals from water vapor photodissociation is a critical factor controlling the atmospheric CH4 abundance. Consequently, atmospheric CH4 partial pressure (pCH4) on inhabited Earth-like exoplanets orbiting Sun-like stars (F-, G-, and K-type stars) would be controlled primarily by stellar irradiance. Specifically, irradiance at wavelengths of approximately 200–210 nm is a major controlling factor for atmospheric pCH4 when the carbon dioxide partial pressure is sufficiently high to absorb most stellar irradiance at 170–200 nm. Finally, we also demonstrated that inhabited exoplanets orbiting near the outer edge of K-type stars’ habitable zones are better suited for atmospheric pCH4 buildup. Such properties will provide valuable support for future detection of life signatures.

Carbon Cycle Instability for High-CO2 Exoplanets: Implications for Habitability

Implicit in the definition of the classical circumstellar habitable zone (HZ) is the hypothesis that the carbonate-silicate cycle can maintain clement climates on exoplanets with land and surface water across a range of instellations by adjusting atmospheric CO2 partial pressure (pCO2). This hypothesis is made by analogy to the Earth system, but it is an open question whether silicate weathering can stabilize climate on planets in the outer reaches of the HZ, where instellations are lower than those received by even the Archean Earth and CO2 is thought likely to dominate atmospheres. Since weathering products are carried from land to ocean by the action of water, silicate weathering is intimately coupled to the hydrologic cycle, which intensifies with hotter temperatures under Earth-like conditions. Here, we use global climate model simulations to demonstrate that the hydrologic cycle responds counterintuitively to changes in climate on planets with CO2-H2O atmospheres at low instellations and high pCO2, with global evaporation and precipitation decreasing as pCO2 and temperatures increase at a given instellation. Within the Maher & Chamberlain (or MAC) weathering formulation, weathering then decreases with increasing pCO2 for a range of instellations and pCO2 typical of the outer reaches of the HZ, resulting in an unstable carbon cycle that may lead to either runaway CO2 accumulation or depletion of CO2 to colder (possibly snowball) conditions. While the behavior of the system has not been completely mapped out, the results suggest that silicate weathering could fail to maintain habitable conditions in the outer reaches of the nominal HZ.

Exploring the Effects of Stellar Magnetism on the Potential Habitability of Exoplanets

Considerable interest has centered on Earth-like planets orbiting in the circumstellar habitable zone (CHZ) of its star. However, the potential habitability of an exoplanet depends upon a number of additional factors, including the presence and strength of any planetary magnetic field and the interaction of this field with that of the host star. Not only must the exoplanet have a strong enough magnetic field to shield against stellar activity, but it must also orbit far enough from the star to avoid direct magnetic connectivity. We characterize stellar activity by the star’s Rossby number, Ro, the ratio of stellar rotation rate to convective turnover time. We employ a scaled model of the solar magnetic field to determine the star’s Alfvén radius, the distance at which the stellar wind becomes super-Alfvénic. Planets residing within the Alfvén surface may have a direct magnetic connection to the star and therefore not be the most viable candidates for habitability. Here, we determine the Rossby number of a sample of 1053 exoplanet-hosting stars for which the rotation rates have been observed and for which a convective turnover time can be calculated. We find that 84 exoplanets in our sample have orbits which lie inside the CHZ and that also lie outside the star’s Alfvén surface: 34 of these have been classified as terran (11) or superterran (23) planets. Applying the Alfvén surface habitability criterion yields a subset of the confirmed exoplanets that may be optimal targets for future observations in the search for signatures of life.

How the presence of a giant planet affects the outcome of terrestrial planet formation simulations

The architecture and masses of planetary systems in the habitable zone could be strongly influenced by the presence of outer giant planets. Here, we investigate the impact of outer giants on terrestrial planet formation, under the assumption that the final assembly of the planetary system is set by a giant impact phase. Utilizing a state-of-the-art N-body simulation software, GENGA, we interpret how the late stage of terrestrial planet formation contributes to diversity among planetary systems. We designed two global model setups: 1) we placed a gas giant on the outer side of planetesimals and embryo disk and 2) we only included planetesimals and embryos, but no giant. For the model including the outer giant, we studied the effect of different giant initial masses in the range of 1.0–3.0 Jupiter masses, as well as a range of orbital radii from 2.0–5.8 AU. We also studied the influence of different initial positions of planetesimals and embryos on the results. Our N-body simulation time is approximately 50 Myr. The results show that the existence of an outer giant will promote the interaction between planetesimals and embryos, making the orbits of the formed terrestrial planets more compact. However, placing the giant planet too close to the planetesimals and embryo disk suppresses the formation of massive rocky planets. In addition, under the classical theory, where planetary embryos and planetesimals collide to form terrestrial planets, our results show that the presence of a giant planet actually decreases the gap complexity of the inner planetary system.

Improving Earth-like planet detection in radial velocity using deep learning

Context. Many novel methods have been proposed to mitigate stellar activity for exoplanet detection as the presence of stellar activity in radial velocity (RV) measurements is the current major limitation. Unlike traditional methods that model stellar activity in the RV domain, more methods are moving in the direction of disentangling stellar activity at the spectral level. As deep neural networks have already been proven to be one of the most effective tools in data mining, in this work, we explore their potential in the context of Earth-like planet detection in RV measurements. Aims. The goal of this paper is to present a novel convolutional neural network-based algorithm that efficiently models stellar activity signals at the spectral level, enhancing the detection of Earth-like planets. Methods. Based on the idea that the presence of planets can only produce a Doppler shift at the spectral level while the presence of stellar activity can introduce a variation in the profile of spectral lines (asymmetry and depth change), we trained a convolutional neural network to build the correlation between the change in the spectral line profile and the corresponding RV, full width at half maximum (FWHM) and bisector span (BIS) values derived from the classical cross-correlation function. Results. This algorithm has been tested on three intensively observed stars: Alpha Centauri B (HD 128621), Tau ceti (HD 10700), and the Sun. By injecting simulated planetary signals at the spectral level, we demonstrate that our machine learning algorithm can achieve, for HD 128621 and HD 10700, a detection threshold of 0.5 m s−1 in semi-amplitude for planets with periods ranging from 10 to 300 days. This threshold would correspond to the detection of a ~4 M⊕ in the habitable zone of those stars. On the HARPS-N solar dataset, thanks to significantly more data, our algorithm is even more efficient at mitigating stellar activity signals and can reach a threshold of 0.2 m s−1, which would correspond to a 2.2 M⊕ planet on the orbit of the Earth. Conclusions. To the best of our knowledge, it is the first time that such low detection thresholds are reported for the Sun, but also for other stars, and therefore this highlights the efficiency of our convolutional neural network-based algorithm at mitigating stellar activity in RV measurements.