In the short-season winter environment of India and Bangladesh, lentil growth and seed yield are significantly hindered by foliar blight caused by Stemphylium botryosum. As the international germplasm pool lacks a resistance source, the study aims to develop a mutant population to identify a high-yielding mutant resistance against the pathogen. A gamma-irradiated population was developed based on its GR50 dose of 248.8 Gy. The screening of almost 130,000 M2 plants identified a tolerant lentil mutant, MM216. The multi-location trials revealed that MM216 showed an impressive and robust resistance; the selected mutant line could be recommended as a donor in the lentil breeding program against the pathogen globally. A 100 g seed was exposed to a GR50 dose to develop the M1 population. At maturity, at least 100 M2 seeds of each 1300 M1 plant were harvested individually. So, almost 130,000 M2 plants were screened in the disease hot spot. The selected mutants were advanced to M7 by screening in the field and challenged in controlled conditions with the pure pathogen isolate. A resistance mutant, MM216, with a per cent disease index (PDI) of 55. The resistance ability was confirmed further in controlled conditions. The fungal and plant DNA ratio was almost negligible in the tolerant mutant, whereas it was 0.17 in WBL77 at 196 h post-inoculation. The selected mutant did not display any yield penalty, but there was a delay in flowering by a week compared to WBL77.

Artificial intelligence (AI) accelerates the traditional way of farming by implementing modern approaches that enhance production, minimise resources, and improve predictive decision-making ability in the domain of agriculture. It also enables better solutions for various environmental problems. Generative artificial intelligence (GenAI) is an advanced subset of artificial intelligence that enables emerging technologies that support sustainable crop management, effective biodiversity conservation, contributing to economic development by utilising a range of predictive models, including Generative Adversarial Networks (GANs), Autoencoders, Transformers, Diffusion Models, and Autoregressive models, as well as the real-time object detection algorithm YOLO (You Only Look Once), GenAI transforming crop management by enabling predictions of crop yields, facilitating weed control, diagnosing diseases, and supporting precision farming. Integration of GenAI, machine learning (ML), and deep learning (DL) with IoT (Internet of Things) devices opens up a new avenue in the sector of digital agriculture to facilitate real-time decision-making. Traditional farming is no longer adequate to satisfy consumer demand, and crop management can often be complicated and laborious; therefore, it is necessary to integrate traditional agriculture with modern computerised technologies such as GenAI to increase crop management efficiency and stimulate changes in the agribusiness sectors—even among rural farming communities. This chapter has demonstrated the need for GenAI tools in solving environmental issues, including agriculture, providing an overview of the processes, current applications, further potential applications, and limitations of GenAI tools in agriculture and other problems related to the environment. GenAI could potentially be a revolutionary force, enhancing human resilience and managing food security.