• Rural Digital Europe
• Publications close
• ZA close

The current reliance on pesticides and synthetic fertilizers has been vital to sustain and increase agricultural production. The continuous, excessive use of these traditional practices has negatively affected consumer health and burdened the ecosystem. The use of plant extracts as a tool to minimize agrochemical inputs has been extensively investigated; these extracts have the ability to improve both plant growth and agricultural productivity. Therefore, this study was conducted to determine the effect of foliar plant extract application on potato growth, as well as on certain physiological and yield attributes. From four weeks after planting onwards, five healthy, equal-sized potato plants per treatment received various foliar plant extract applications. These extracts included brown seaweed Ascophyllum nodosum extract (ANE), aloe vera leaf extract (AVE), garlic bulb extract (GBE), and moringa leaf extract (MLE). The treatments were repeated weekly until harvesting. Application data regarding growth and physiological parameters were collected weekly. The pre-harvest foliar application of various plant extracts significantly enhanced (p ≤ 0.05) the plant growth, physiological, and yield attributes of potatoes. The best growth and yield responses were observed following ANE and MLE application. Plant extracts have shown beneficial effects on other crops as well, but further validation of these effects is still necessary in order to popularize and commercialize such applications.

The article provided insights into why local government and service delivery must be rethought in light of digital transformation. It exposed the significance of digital transformation in solving local government and service delivery challenges. The article followed a qualitative research approach. It employed document analysis and literature review as data collection instruments. It argued that digital transformation can help local governments in South Africa fulfil constitutional obligations and meet policy goals. It demonstrated how digitally transformed local government can solve service delivery problems through the deployment of digital technologies that improve decision-making, cut costs, streamline operations, and offer efficient services. The article revealed that the digital divide, lack of technical expertise, data security concerns and resource constraints are some of the challenges that can affect the digital transformation of local government and service delivery in South Africa. These challenges must be resolved for digital transformation to play a significant role in improving the effectiveness of local government in service delivery. The article recommended that local governments in South Africa digitally transform in ways that foster equality and deliver local government services to all citizens. The article contributes to scholarship advocating for public sector innovation broadly, and specifically, illustrates the criticality of embracing digital transformation of local government and service delivery. Keywords: Digital Transformation, Digital Technologies, Local Government, South Africa, Service Delivery

South Africa’s location-specific opportunities have enabled local researchers to establish a niche in the robotics community.

Societal Impact StatementThe relationship between rainfall, fire and habitat can display incongruencies. The 2021 Malagasy Grassy Biomes Workshop identified understanding fire regimes as a knowledge gap. This study pinpoints regions where anthropogenic fire has the potential to transform or has transformed habitat to treeless‐grassland, by identifying landscape‐scale, island‐wide fire anomalies across half of Madagascar. Its eastern forests burn like savannas, and central‐western grasslands burn frequently and intensely despite receiving rainfall usually associated with forest and fire‐absence. Recognising the incongruity and better understanding its drivers can mitigate against landscape‐scale degradation, improving ecological function, and human well‐being.Summary Data show that since 1953, human‐lit fires on Madagascar have transformed clear‐cut forest to treeless‐grasslands. To address the extent of Malagasy treeless‐grasslands at human settlement, the 2021 Malagasy Grassy Biomes Workshop identified the role of fire as a critical knowledge‐gap for understanding ecological function. The relationship between mean annual precipitation (MAP), fire and habitat is well established across mesic systems. Anthropogenically transformed habitats often deviate from expected ecological patterns, so we tested for landscape‐scale, island‐wide MAP‐related fire and habitat anomalies. We collated Malagasy fire, habitat and MAP datasets, identifying location and scale of incongruities relative to global fire‐habitat‐MAP expectations. Next, we tested for mismatches in fire regimes (frequency, timing, extent and intensity of fires) between Malagasy and equivalent global biomes, using global, comprehensive landscape‐scale fire regime data. Across half of Madagascar, fire frequency and habitat are decoupled from MAP, and fire regimes across Malagasy ecoregions differ significantly from those in shared biomes elsewhere in the world. Landscape‐scale incongruities span Malagasy eastern forests (which burn like savanna systems) and central‐western treeless‐grasslands, which burn frequently and intensely despite receiving MAP typical of forest presence and fire‐absence, globally. Fire‐MAP incongruities identify potentially transformed areas, or those undergoing transformation by fire, and establish a platform for investigating the nuanced social, political and ecological dynamics that may contribute to and perpetuate these anomalies. Incongruities also highlight the anthropogenic landscape degradation associated with fire anomalies. Addressing these impacts can facilitate restoration of ecological function, productivity and food security, benefiting biodiversity and humans at multiple scales.

In the realm of solar photovoltaic system image segmentation, existing deep learning networks focus almost exclusively on single image sources both in terms of sensors used and image resolution. This often prevents the wide deployment of such networks. Our research introduces a novel approach to train a network on a diverse range of image data, spanning UAV, aerial, and satellite imagery at both native and aggregated resolutions of 0.1 m, 0.2 m, 0.3 m, 0.8 m, 1.6 m, and 3.2 m. Using extensive hyperparameter tuning, we first determined the best possible parameter combinations for the network based on the DeepLabV3 ResNet101 architecture. We then trained a model using the wide range of different image sources. The final network offers several advantages. It outperforms networks trained with single image sources in multiple test applications as measured by the F1-Score (95.27%) and IoU (91.04%). The network is also able to work with a variety of target imagery due to the fact that a diverse range of image data was used to train it. The model is made freely available for further applications.

Summary Fynbos, a shrubland from the Cape Floristic Region in South Africa, is one of five Mediterranean-climate biomes alongside maquis in the Mediterranean Basin, chaparral in California, matorral in Central Chile and kwongan in Southwestern Australia. We compiled the available information on the wood anatomy of 226 species belonging to 65 genera of 14 families that occurred in fynbos and compared this dataset with the published data on wood diversity in Californian chaparral and Israeli maquis. “Carlquist’s Law”, i.e., the association between the ground tissue made of fibre tracheids and low vessel grouping, has been confirmed for the fynbos plants. The lack of ring porosity and very low incidence of semi-ring-porous woods is the most prominent difference of the fynbos from the other two vegetation types. These features are attributed to the paucity of deciduous plants in fynbos which is probably associated with the poor-nutrient soils in this biome. The fynbos differs from chaparral and maquis also in the greatest percentage of the species having no tracheids in their wood as well as with the lowest incidence of helical thickenings on the vessel walls. These differences could be explained by the lower tolerance of fynbos shrubs to seasonal drought due to the relatively mild dry season in this biome. We also found that some differences between fynbos, chaparral, and maquis in the incidences of fibre tracheids and vasicentric/vascular tracheids associated with large vessel groups can be at least partly explained by different systematic compositions of their floras. The higher percentage of distinct growth rings, greater vessel diameter, and lower vessel frequency in maquis compared with fynbos and chaparral can be attributed to a common occurrence of relatively tall trees in this vegetation.

In the past few years, privacy concerns have grown, making the financial models of businesses more vulnerable to attack. In many cases, it is hard to emphasize the importance of monitoring things in real-time with data from Internet of Things (IoT) devices. The people who make the IoT devices and those who use them face big problems when they try to use Artificial Intelligence (AI) techniques in real-world applications, where data must be collected and processed at a central location. Federated learning (FL) has made a decentralized, cooperative AI system that can be used by many IoT apps that use AI. It is possible because it can train AI on IoT devices that are spread out and do not need to share data. FL allows local models to be trained on local data and share their knowledge to improve a global model. Also, shared learning allows models from all over the world to be trained using data from all over the world. This article looks at the IoT in all of its forms, including “smart” businesses, “smart” cities, “smart” transportation, and “smart” healthcare. This study looks at the safety problems that the federated learning with IoT (FL-IoT) area has brought to market. This research is needed to explore because federated learning is a new technique, and a small amount of work is done on challenges faced during integration with IoT. This research also helps in the real world in such applications where encrypted data must be sent from one place to another. Researchers and graduate students are the audience of our article.

Об’єктом цього дослідження є впровадження Інтернету речей (IoT) та його вплив на організаційну ефективність малих та середніх підприємств (МСП) у країнах з перехідною економікою. МСП в країнах з перехідною економікою стикаються з низьким рівнем ефективності через технологічні обмеження, недостатньо кваліфіковані людські ресурси, низький рівень підприємницьких здібностей та систем управління, дефіцит доступної інформації, недостатнє використання інформаційних технологій, низьку якість продукції та відсутність стратегічних довгострокових планів. Для виявлення, оцінки та узагальнення результатів усіх відповідних індивідуальних досліджень на теми четвертої промислової революції (4ПР), Інтернету речей, організаційної ефективності та МСП було використано метод систематичного огляду літератури. Було знайдено 461 статтю, з яких 60 статей були використані в якості вибірки для цього дослідження. Результати цього дослідження показали, що впровадження Інтернету речей позитивно впливає на ефективність роботи МСП у країнах з перехідною економікою. Результати також показують, що фінансові, технологічні та операційні ризики є основними ризиками, з якими стикаються МСП при впровадженні технологій Інтернету речей в країнах з перехідною економікою. Суть результатів полягає в тому, щоб внести свій вклад в існуючі знання, надавши цікаву інформацію у вигляді концепції про те, як технології Інтернету речей можуть бути застосовані для підвищення ефективності роботи МСП в країнах з економікою, що розвивається. Це досягається шляхом ознайомлення МСП з їх потенційними перевагами, наданням певних знань щодо забезпечення фінансових ресурсів та здатності аналізувати зовнішнє середовище, а також пролиттям світла на переваги та можливості, які пропонують ці нові інструменти, і на те, як вони можуть згодом покращити ефективність роботи МСП. Більшість статей, що використовувалися для систематичного огляду літератури, були з розвинених країн, оскільки література, яка б розповідала про ІоТ та ефективність МСП у країнах з перехідною економікою, була обмеженою. Тому дослідження було зосереджене на ІоТ і на тому, як він може покращити організаційну ефективність МСП в країнах з перехідною економікою. The object of this research is the implementation of Internet of Things (IoT) and its effect on organizational performance for Small and Medium Enterprises (SMEs) in emerging economies. SMEs in emerging economies are faced with low level of performance due to technological constraint, inadequate skilled human resource, lower entrepreneurial capabilities and management systems, the deficiency of available information, inadequate use of Information Technology, poor quality products and lack of strategic long-term plans. Systematic literature reviews approach was used to discover, assess and synthesize findings of all relevant individual research on fourth industrial revolution (4IR), IoT, organization performance and SMEs topics. 461 articles were found, and 60 articles were used as sample of this study. Findings of this study established that implementation of IoT positively affects performance for SMEs in emerging economies. Results also shows that financial, technological, and operational risks are major risks faced by SMEs in implementing IoT technologies in emerging economies. The essence of the results is to contribute to current body of knowledge by giving interesting insights in the form of a framework on how IoT technologies can be applied in enhancing SMEs performance in emerging economies. This is achieved by making SMEs aware of its potential benefit by providing some knowledge on securing financial resources, and ability to analyse external environment, and to shed more light on the benefits and opportunities that these new tools offer and how it can subsequently improve organization performance for SMEs. Most articles used systematic literature review were from developed economies as there was limited literature which speaks about IoT and SMEs performance in emerging economies. The study therefore focused on IoT and how it can improve SMEs’ organizational performance in emerging economies.

Remote sensing data is a cheap form of surficial geoscientific data, and in terms of veracity, velocity and volume, can sometimes be considered big data. Its spatial and spectral resolution continues to improve over time, and some modern satellites, such as the Copernicus Programme's Sentinel-2 remote sensing satellites, offer a spatial resolution of 10 m across many of their spectral bands. The abundance and quality of remote sensing data combined with accumulated primary geochemical data has provided an unprecedented opportunity to inferentially invert remote sensing data into geochemical data. The ability to derive geochemical data from remote sensing data would provide a form of secondary big geochemical data, which can be used for numerous downstream activities, particularly where data timeliness, volume and velocity are important. Major benefactors of secondary geochemical data would be environmental monitoring and applications of artificial intelligence and machine learning in geochemistry, which currently entirely relies on manually derived data that is primarily guided by scientific reduction. Furthermore, it permits the usage of well-established data analysis techniques from geochemistry to remote sensing that allows useable insights to be extracted beyond those typically associated with strictly remote sensing data analysis. Currently, no generally applicable and systematic method to derive chemical elemental concentrations from large-scale remote sensing data have been documented in geosciences. In this paper, we demonstrate that fusing geostatistically-augmented geochemical and remote sensing data produces an abundance of data that enables a more generalized machine learning-based geochemical data generation. We use gold grade data from a South African tailing storage facility (TSF) and data from both the Landsat-8 and Sentinel remote sensing satellites. We show that various machine learning algorithms can be used given the abundance of training data. Consequently, we are able to produce a high resolution (10 m grid size) gold concentration map of the TSF, which demonstrates the potential of our method to be used to guide extraction planning, online resource exploration, environmental monitoring and resource estimation. Validerad;2023;Nivå 1;2023-04-12 (hanlid);Funder: Department of Scienceand Innovation (DSI) - National Research Foundation (NRF) ThuthukaGrant (121,973); SI-NRF CIMERA; Centre for Advanced Miningand Metallurgy (CAMM), Luleå University of Technology; Sibanye-Stillwater Ltd