Data Generation Tool Research Articles

Strategical and tactical supply chain optimisation for smart production planning and control 4.0

Industry 4.0 (I4.0) technologies generate new opportunities for developing smart models, algorithms and tools to support supply chain (SC) production planning and control (PPC), or smart PPC (SPPC 4.0). Paired with opportunities, challenges arise in integrating sustainability and resilience in SC network design (SCND) according under I4.0. The main novelty of this paper is to propose two multi-objective models that integrate strategical and tactical PPC decisions into a sustainable-resilient SC under I4.0 towards SPPC 4.0. Sustainability is incorporated in terms of reducing costs and CO2 emissions, and a job creation factor. Resilience is incorporated in terms of contracting support suppliers. To solve the multi-objective models, the augmented epsilon constraint method (AUGMECON) was used. This algorithm minimises a target objective function while it treats the others as constraints. Our experiments indicate that AUGMECON is sensitive to the choice of epsilon values. Furthermore, a synthetic data generation tool called SR1-SR2_SynthDataGenerator was developed. This tool generates input datasets to validate and evaluate our models against benchmarks. A stochastic model (SR2) is also proposed that, with small datasets, takes 8.39 seconds to solve. The proposed models can be useful for industries that seek sustainable and resilient SCs to adapt to changing environments.

Bolus tracking from pulsed x-ray projections: A feasibility study using a five-dimensional cardiac CT contrast dynamics model.

Cardiac computed tomography (CT) exams are some of the most complex CT exams due to the need to carefully time the scan when the heart chambers are near the peak contrast concentration. With current "bolus tracking" and "timing bolus" techniques, after contrast medium is injected, a target vessel or chamber is scanned periodically, and images are reconstructed to monitor the opacification. Both techniques have opportunities for improvement, such as reducing the contrast medium volume, the exam time, the number of manual steps, and improving the robustness of correctly timing the peak opacification. The objective of our study is to (1) develop a novel autonomous cardiac CT clinical workflow to track contrast bolus dynamics directly from pulsed x-ray projections, (2) develop a new five-dimensional virtual cardiac CT data generation tool with programmable cardiac profiles and bolus dynamics, and (3) demonstrate the feasibility of projection-domain prospective bolus tracking using a neural network trained and tested with the virtual data to find the contrast peak. In our proposed workflow, pulsed mode projections (PMPs) are acquired with a wide-open collimator under sparse view conditions (monitoring phase). Each time a new PMP is acquired, the neural network is used to estimate the contrast enhancement inside the target chambers. To train such a network, we introduce a new approach to generate clinically realistic virtual scan data based on a five-dimensional cardiac model, by synthesizing user-defined contrast bolus dynamics and patient electrocardiogram profiles. In this study, we investigated a scenario with one single PMP per rotation. To find the optimal PMP view angle, 20 angles were explored. For each angle, 300 virtual exams were generated from 115 human subject datasets and divided into training, validation, and testing groups. Twenty neural networks were trained and evaluated in total to find the optimal network. Finally, a simple bolus peak time estimation algorithm was developed and evaluated by comparing to the ground truth bolus peak time. To evaluate the accuracy of a bolus time-intensity curve estimated by the network, the cosine similarity between the estimation and the ground truth was computed. The cosine similarity was larger than 0.97 for all projection angles. A view angle corresponding to the x-ray tube at 30 degrees from vertical (left-anterior of subject) showed the lowest errors. The amplitude of the estimated bolus curves (in Hounsfield Units) was not always correctly predicted, but the shape was accurately predicted. This resulted in an RMSE of 1.23s for the left chambers and 0.78s for the right chambers in the contrast peak time estimation. In this study, we proposed an innovative real-time way to predict the contrast bolus peak in cardiac CT as well as an innovative approach to train a neural network using virtual but clinically realistic data. Our trained network successfully estimated the shape of the time-intensity curve for the target chambers, which led to accurate bolus peak time estimation. This technique could be used for autonomous diagnostic cardiac CT to trigger a diagnostic scan for optimal contrast enhancement.

Robust anomaly detection via adversarial counterfactual generation

The capability to devise robust outlier and anomaly detection tools is an important research topic in machine learning and data mining. Recent techniques have been focusing on reinforcing detection with sophisticated data generation tools that successfully refine the learning process by generating variants of the data that expand the recognition capabilities of the outlier detector. In this paper, we propose ARN\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extrm{ARN}$$\\end{document}, a semi-supervised anomaly detection and generation method based on adversarial counterfactual reconstruction. ARN\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ extrm{ARN}$$\\end{document} exploits a regularized autoencoder to optimize the reconstruction of variants of normal examples with minimal differences that are recognized as outliers. The combination of regularization and counterfactual reconstruction helps to stabilize the learning process, which results in both realistic outlier generation and substantially extended detection capability. In fact, the counterfactual generation enables a smart exploration of the search space by successfully relating small changes in all the actual samples from the true distribution to high anomaly scores. Experiments on several benchmark datasets show that our model improves the current state of the art by valuable margins because of its ability to model the true boundaries of the data manifold.

Self-efficacy Activation Factors: Analysis of Saudi English Language Learners' Self- Efficacious Discourse

This qualitative study aims at investigating Saudi English language learners' self-efficacy activation factors. Seventy-eight participants were recruited through random sampling wherein 46 belonged to English department, 20 belonged to Computer Science department, and 12 were enrolled in Business Management Diploma at King Khalid University, Saudi Arabia. Initially, classroom observation was carried out to identify the items for the unstructured questionnaire. Unstructured questionnaire and interviews were employed as the main data generation tools. Content analysis was employed to the participants' self-efficacious discourse derived from the data which revealed three main themes: 1) ideological beliefs activated learners’ self-efficacy; 2) good management of time improved language learning outcomes; and 3) teachers’ active role in engaging the learners in language practicing sessions and in LMS activated their self-efficacy. Bandura's triadic reciprocal determinism framework was incorporated in the analysis and discussion of the participants' discourse in relation to the emerged themes. The twofold analysis revealed learners' ideological beliefs as the main psychological factor; time management as the main personal factor; and learners' engagement in technologically assisted learning (LMS) as the main environmental factor that constituted learners' reciprocal determinism for achieving the language learning outcomes.

Challenges in IBD Research 2024: Precision Medicine.

Precision medicine is part of 5 focus areas of the Challenges in IBD Research 2024 research document, which also includes preclinical human IBD mechanisms, environmental triggers, novel technologies, and pragmatic clinical research. Building on Challenges in IBD Research 2019, the current Challenges aims to provide a comprehensive overview of current gaps in inflammatory bowel diseases (IBDs) research and deliver actionable approaches to address them with a focus on how these gaps can lead to advancements in interception, remission, and restoration for these diseases. The document is the result of multidisciplinary input from scientists, clinicians, patients, and funders, and represents a valuable resource for patient-centric research prioritization. In particular, the precision medicine section is focused on the main research gaps in elucidating how to bring the best care to the individual patient in IBD. Research gaps were identified in biomarker discovery and validation for predicting disease progression and choosing the most appropriate treatment for each patient. Other gaps were identified in making the best use of existing patient biosamples and clinical data, developing new technologies to analyze large datasets, and overcoming regulatory and payer hurdles to enable clinical use of biomarkers. To address these gaps, the Workgroup suggests focusing on thoroughly validating existing candidate biomarkers, using best-in-class data generation and analysis tools, and establishing cross-disciplinary teams to tackle regulatory hurdles as early as possible. Altogether, the precision medicine group recognizes the importance of bringing basic scientific biomarker discovery and translating it into the clinic to help improve the lives of IBD patients.

Simulation-based evaluation of indoor positioning systems in connected aircraft cabins

With regard to the demanding aircraft cabin environment, this paper delves into the rising use of location-aware radio communication systems to streamline operational processes. We propose a hybrid deterministic and stochastic simulation approach, incorporating model-based ray-tracing and empirical residual simulation. The methodology presented allows for the evaluation of localization methods based on geometric relations, serving as both a data generation and validation tool. We elaborate how different radio properties and propagation phenomena influence these geometric relations and the localization process. This paper includes a publicly available dataset derived from the simulation approach, facilitating transparency and further analysis in the field of aircraft cabin radio localization systems.

Investigating the Roles and Responsibilities of Institutional Signing Officials After Data Sharing Policy Reform for Federally Funded Research in the United States: National Survey.

New federal policies along with rapid growth in data generation, storage, and analysis tools are together driving scientific data sharing in the United States. At the same, triangulating human research data from diverse sources can also create situations where data are used for future research in ways that individuals and communities may consider objectionable. Institutional gatekeepers, namely, signing officials (SOs), are therefore at the helm of compliant management and sharing of human data for research. Of those with data governance responsibilities, SOs most often serve as signatories for investigators who deposit, access, and share research data between institutions. Although SOs play important leadership roles in compliant data sharing, we know surprisingly little about their scope of work, roles, and oversight responsibilities. The purpose of this study was to describe existing institutional policies and practices of US SOs who manage human genomic data access, as well as how these may change in the wake of new Data Management and Sharing requirements for National Institutes of Health-funded research in the United States. We administered an anonymous survey to institutional SOs recruited from biomedical research institutions across the United States. Survey items probed where data generated from extramurally funded research are deposited, how researchers outside the institution access these data, and what happens to these data after extramural funding ends. In total, 56 institutional SOs participated in the survey. We found that SOs frequently approve duplicate data deposits and impose stricter access controls when data use limitations are unclear or unspecified. In addition, 21% (n=12) of SOs knew where data from federally funded projects are deposited after project funding sunsets. As a consequence, most investigators deposit their scientific data into "a National Institutes of Health-funded repository" to meet the Data Management and Sharing requirements but also within the "institution's own repository" or a third-party repository. Our findings inform 5 policy recommendations and best practices for US SOs to improve coordination and develop comprehensive and consistent data governance policies that balance the need for scientific progress with effective human data protections.

Threshold Effects on Outlier Detection: A Comparative Study of MCD and MRCD Estimators in Multivariate Data Analysis

Aims: The aim of this study is to investigate the impact of thresholds on the detection of outliers by comparing the performance of two estimators, namely the minimum covariance determinant (MCD) and minimum regularized covariance determinant (MRCD), at different sample sizes. The study uses simulated data generated from the standard normal distribution to assess how varying thresholds affect the ability of these estimators to detect outliers.
 Study Design: This study employs a quantitative research design. It involves the generation of simulated data, the application of the MCD and MRCD estimators for outlier detection, and the systematic manipulation of thresholds and sample size as independent variables.
 Place and Duration: The study is conducted using computational tools and did not require a physical location.
 Methodology: Simulated data is generated from the standard normal distribution to create a controlled environment for outlier detection experiments. The MCD and MRCD estimators are applied to the simulated data to detect outliers. These estimators are sensitive to deviations from the norm in the data. Different thresholds are systematically applied to the data, and the performance of the estimators is assessed at each threshold level. Thresholds may vary in their extremeness. The study investigates the impact of different sample sizes on outlier detection. This involves using datasets with varying numbers of observations. The r programming language and associated packages are used as the statistical tool for data generation, analysis, and visualization.
 Results: The study's findings indicate that the choice of thresholds in data analysis significantly affects the performance of the MCD and MRCD estimators in outlier detection. If the thresholds used for both estimators are the same, their performance is similar. However, differences emerge when thresholds differ from each other. Higher thresholds are shown to identify less extreme outliers, while lower thresholds are effective at identifying more extreme outliers. These results provide insights into the behavior of these estimators in outlier detection scenarios, shedding light on their sensitivity to threshold choices and sample size.Conclusion: Our study has shed light on the critical interdependencies among threshold choices, sample sizes, and the performance of the minimum covariance determinant (MCD) and minimum regularized covariance determinant (MRCD) estimators in the context of outlier detection. By conducting a systematic exploration in a controlled environment with simulated data, we have gleaned valuable insights that can inform both researchers and practitioners in the field of organizational science research.

Modelling the perception of visual design principles on façades through fuzzy sets: towards building an automated architectural data generation and labelling tool

Recent studies showed that deep learning techniques and image processing can identify the distinguishing design principles in architectural façades. However, predicting the strength of a principle is still a challenging task, as it requires a huge amount of annotated design variations. The difficulties in both searching such big numbers of data – and its labelling by experts – slow down the research. This paper proposes a computation approach for obtaining this type of data faster. With the help of parametric modelling and evolutionary algorithms, we could manipulate the design elements, and thereby generate different solutions. An integrated fuzzy logic decision mechanism could enable to carry human knowledge in the judging and labelling of alternatives automatically. The final synthetic data developed from real building images could be used for machine learning applications to enhance our understanding of artistic expression.

An Introductory Synthetic Data Tool

ObjectivesSynthetic data reproduces features of a dataset without disclosing sensitive information, allowing researchers to explore data structures and test code without requiring access to real, potentially sensitive, data. We produced a low-fidelity synthetic data generation tool, accompanied by extensive documentation, allowing novice and expert users to produce such data.
 MethodsOur tool, consisting of a Python notebook and a user guide, takes a dataset as input, and produces ‘low-fidelity’ synthetic copy of this dataset, recreating the data fields (or columns) of a dataset, as well as the data types and statistical relationships within these fields, but not between them. It has been tested using real-world administrative data sets and with several users, looking at the quality of the data generated, inspecting whether the data is indeed low-fidelity (i.e. statistical relationships between fields are not recreated) and the usability of the tool.
 ResultsOur tool successfully created synthetic datasets from administrative datasets. Users were positive about its usability and the generated data. Tests indicated that computational memory is a main constraint on the size of datatable that can be read in by the tool. We have since implemented improvements to the memory efficiency of the tool to partially address this and have also added procedures that allow for using subsets instead of complete datasets, allowing for the use of datasets which would have otherwise been too large to be used. Testing further indicated that, while the tool by design does not preserve any relationships between fields, they can be reproduced by coincidence, and a limited disclosure process may be required when correlations from the original data are reproduced.
 ConclusionsThe tool is easy to use and therefore a useful introduction to synthetic data, providing users with a foundation before using more sophisticated synthetic data tools like Synthpop. Future work could include the development of a Python library and extension of the tool to handle linked datatables.

Translation Portfolio

In this paper, based on the findings of the first author’s dissertation, we seek to expand the concept of assessment through the Portfolio, adding to the process a practice that has been gaining strength in the post-method era (Kumaravadivelu, 2006) - the translation practice (NORD, 2012) - used in a planned and systematic way (Liberatti, 2012). To this end, we prepared and applied a didactic sequence (Dolz; Noverraz; Schneuwly, 2004; Miquelante; Cristovão; Pontara, 2020), based on the teaching of Languages under the bias of Sociodiscursive Interactionism (Bronckart, 2007), in a context of higher education (Languages and Literature course), where the activities of the modules focus on the translation from the English language to Portuguese of a poem, carried out by the teachers-in-training. The collection of these activities provided the data for a qualitative analysis and the data generation tools for this work are: a) translation portfolio of activities; and b) the didactic sequence created by the authors. This study resulted in evidence of linguistic development and mobilization of language resources in translation activities, thus placing translation activity as a relevant production to compose the assessment portfolio.

Online Audiences and Gatekeeping: User Comments and Their Infulence on Editorial Processes in Newsrooms in Kenya

In Kenyan newsrooms, there has been a debate about keeping the comment section on news websites in the aftermath of Social Media Networks. This allows the media to still collect user opinions without the risk of unregulated third-party comments. This paper sought to establish the nature and influence user comments have on editorial processes and explain what value media houses that have retained the comment section are receiving. To investigate this, the researchers adopted mixed methods research approach (quantitative and qualitative) and concurrent mixed methods research designs. The targeted population was journalists working in media houses that operate in print, broadcast, and digital news websites in Nairobi County. The targeted media houses were: Nation Media Group (NMG), Standard Group (SG), and Radio Africa Group (RAG). The sample size comprised 252 participants for quantitative data, nine key informants for in-depth interviews, and 84 articles for direct content analysis. Surveys and directed content analysis were used as strategies of inquiry. These strategies were aided by questionnaires, in-depth interviews, and code sheets as data generation tools. Statistical Package for Social Sciences (IBM/SPSS) was used to analyse quantitative data. Quantitative data was presented using tables and pie charts. Qualitative data was thematically analysed and presented in the form of themes. Contrary to popular belief, the findings show that discussions in news website comment sections are frequently marred by incivility. Instead, most of the comments were deliberative, with audience members just looking for a forum to express themselves civilly. However, in cases with reported incidences of incivility, the sources quoted were the main trigger. Journalists have been shown to use user input in the comment section to gauge the quality of their content, while media companies use audience knowledge to make strategic decisions. The results shed light on how newsrooms may give the public a platform to discuss and give their input on the news while maintaining deliberative debates.

Professional development for physical education teachers: A participatory approach to identifying learning needs

Predetermined professional development (PD) programmes delivered by external experts are the usual approach to enhancing the teaching of physical education (PE) in disadvantaged school contexts. This generally does not result in sustained learning and development once the PE professionals withdraw. Addressing the lack of teacher- and context-driven PD, we propose an evidence-based, collaborative, and transformative PD approach that involves teachers themselves in designing, implementing, and evaluating ongoing learning opportunities suited to their context. To enable teachers to improve their practice in a sustainable manner, we adopted a participatory action learning and action research design, using qualitative data generation tools. With this article we report on the first cycle, namely that of action and reflection, where teachers generated and analysed qualitative data to identify their learning needs. Four themes emerged, namely (1) the need to interpret and adapt the Curriculum and Assessment Policy Statement (CAPS) (2); ability to teach PE in their specific low-resource context while; (3) generating support from colleagues and management, and (4) coping with systemic issues impacting on their teaching. We discuss the implications of these needs for the continuing PD of teachers.

Who is sensitising whom? A participatory interview guide development as an awareness tool within a health care research project

Who is sensitising whom? A participatory interview guide development as an awareness tool within a health care research project

Scalable modular synthetic data generation for advancing aerial autonomy

One major barrier to advancing aerial autonomy has been collecting large-scale aerial datasets for training machine learning models. Due to costly and time-consuming real-world data collection through deploying drones, there has been an increasing shift towards using synthetic data for training models in drone applications. However, to increase widespread generalization and transferring models to real-world, increasing the diversity of simulation environments to train a model over all the varieties and augmenting the training data, has been proved to be essential. Current synthetic aerial data generation tools either lack data augmentation or rely heavily on manual workload or real samples for configuring and generating diverse realistic simulation scenes for data collection. These dependencies limit scalability of the data generation workflow. Accordingly, there is a major challenge in balancing generalizability and scalability in synthetic data generation. To address these gaps, we introduce a scalable Aerial Synthetic Data Augmentation (ASDA) framework tailored to aerial autonomy applications. ASDA extends a central data collection engine with two scriptable pipelines that automatically perform scene and data augmentations to generate diverse aerial datasets for different training tasks. ASDA improves data generation workflow efficiency by providing a unified prompt-based interface over integrated pipelines for flexible control. The procedural generative approach of our data augmentation is performant and adaptable to different simulation environments, training tasks and data collection needs. We demonstrate the effectiveness of our method in automatically generating diverse datasets and show its potential for downstream performance optimization. Our work contributes to generating enhanced benchmark datasets for training models that can generalize better to real-world situations.Video:youtube.com/watch?v=eKpOh-K-NfQ

WhereWulff: A Semiautonomous Workflow for Systematic Catalyst Surface Reactivity under Reaction Conditions.

This paper introduces WhereWulff, a semiautonomous workflow for modeling the reactivity of catalyst surfaces. The workflow begins with a bulk optimization task that takes an initial bulk structure and returns the optimized bulk geometry and magnetic state, including stability under reaction conditions. The stable bulk structure is the input to a surface chemistry task that enumerates surfaces up to a user-specified maximum Miller index, computes relaxed surface energies for those surfaces, and then prioritizes those for subsequent adsorption energy calculations based on their contribution to the Wulff construction shape. The workflow handles computational resource constraints such as limited wall-time as well as automated job submission and analysis. We illustrate the workflow for oxygen evolution reaction (OER) intermediates on two double perovskites. WhereWulff nearly halved the number of Density Functional Theory (DFT) calculations from ∼240 to ∼132 by prioritizing terminations, up to a maximum Miller index of 1, based on surface stability. Additionally, it automatically handled the 180 additional resubmission jobs required to successfully converge 120+ atoms systems under a 48-h wall-time cluster constraint. There are four main use cases that we envision for WhereWulff: (1) as a first-principles source of truth to validate and update a closed-loop self-sustaining materials discovery pipeline, (2) as a data generation tool, (3) as an educational tool, allowing users (e.g., experimentalists) unfamiliar with OER modeling to probe materials they might be interested in before doing further in-domain analyses, (4) and finally, as a starting point for users to extend with reactions other than the OER, as part of a collaborative software community.

FuzzyGAN: Fuzzy generative adversarial networks for regression tasks

Generative Adversarial Networks (GANs) are well-known tools for data generation and semi-supervised classification. GANs, with less labeled data, outperform Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs) in classification tasks. The success of GANs in classification tasks motivates the development of GAN-based techniques for semi-supervised regression tasks. However, developing GANs for regression introduces two major challenges: (1) inherent instability in the GAN formulation and (2) performing regression and achieving stability simultaneously. This paper introduces techniques that show improvement in the GANs’ regression capability. We bake a differentiable fuzzy logic system at multiple locations in a GAN. The fuzzy logic takes the output of either the generator or the discriminator to predict the output, y, and evaluate the generator’s performance. We outline the results of applying the fuzzy logic system across multiple GANs and summarize each approach’s efficacy. This paper shows that adding a fuzzy logic layer can enhance GAN’s ability to perform regression; the most desirable injection location is problem-specific, and we show this through experiments over various datasets. Besides, we demonstrate empirically that the fuzzy-infused GANs are competitive with the DNNs.

Sim2Real Grasp Pose Estimation for Adaptive Robotic Applications

Adaptive robotics plays an essential role in achieving truly co-creative cyber physical systems. In robotic manipulation tasks, one of the biggest challenges is to estimate the pose of given workpieces. Even though the recent deep-learning-based models show promising results, they require an immense dataset for training. In this paper, two vision-based, multi-object grasp pose estimation models (MOGPE), the MOGPE Real-Time and the MOGPE High-Precision are proposed. Furthermore, a sim2real method based on domain randomization to diminish the reality gap and overcome the data shortage. Our methods yielded an 80% and a 96.67% success rate in a real-world robotic pick-and-place experiment, with the MOGPE Real-Time and the MOGPE High-Precision model respectively. Our framework provides an industrial tool for fast data generation and model training and requires minimal domain-specific data.

The role of computational intelligence techniques in the advancements of solar photovoltaic systems for sustainable development: a review

The use of computational intelligence (CI) in solar photovoltaic (SPV) systems has been on the rise due to the increasing computational power, advancements in power electronics and the availability of data generation tools. CI techniques have the potential to reduce energy losses, lower energy costs, and facilitate and accelerate the global adoption of solar energy. In this context, this review paper aims to investigate the role of CI techniques in the advancements of SPV systems. The study includes the involvement of CI techniques for parameter identification of solar cells, PV system sizing, maximum power point tracking (MPPT), forecasting, fault detection and diagnosis, inverter control and solar tracking systems. A performance comparison between CI techniques and conventional methods is also carried out to prove the importance of CI in SPV systems. The findings confirmed the superiority of CI techniques over conventional methods for every application studied and it can be concluded that the continuous improvements and involvement of these techniques can revolutionize the SPV industry and significantly increase the adoption of solar energy.

Environmental Education efforts in a rural drought-prone district in Zimbabwe: Micro innovations with growth potential

In Sub-Saharan Africa, climate change is evident due to the frequency of drought cycles. This paper explores the Environmental Education (EE) efforts for reducing the impact of climate change in drought prone Gwanda district, Zimbabwe. The paper focuses on how climate change mitigation and adaptation stakeholders within the community can initiate EE programs which have the potential to be upscaled to macro innovations. A qualitative interpretive case study approach was used with three data generation tools (interviews, a focus group discussion and document analysis). The sample comprised 38 participants. The study was guided by the Sustainable Rural Livelihoods Framework (1998). The study revealed that for EE programmes to be effective, they have to harness local factors. The study found that formal field days, information and skills sharing among neighbours during letsema/lidaba and Indigenous Knowledge Systems were micro innovations with growth potential to build farmers’ generative resilience to climate change.