English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Agricultural management, with a particular focus on fertilization strategies,holds a central role in shaping crop yield, economic profitability, andenvironmental sustainability. While conventional guidelines offer valuableinsights, their efficacy diminishes when confronted with extreme weatherconditions, such as heatwaves and droughts. In this study, we introduce aninnovative framework that integrates Deep Reinforcement Learning (DRL) withRecurrent Neural Networks (RNNs). Leveraging the Gym-DSSAT simulator, we trainan intelligent agent to master optimal nitrogen fertilization management.Through a series of simulation experiments conducted on corn crops in Iowa, wecompare Partially Observable Markov Decision Process (POMDP) models with MarkovDecision Process (MDP) models. Our research underscores the advantages ofutilizing sequential observations in developing more efficient nitrogen inputpolicies. Additionally, we explore the impact of climate variability,particularly during extreme weather events, on agricultural outcomes andmanagement. Our findings demonstrate the adaptability of fertilization policiesto varying climate conditions. Notably, a fixed policy exhibits resilience inthe face of minor climate fluctuations, leading to commendable corn yields,cost-effectiveness, and environmental conservation. However, our studyilluminates the need for agent retraining to acquire new optimal policies underextreme weather events. This research charts a promising course towardadaptable fertilization strategies that can seamlessly align with dynamicclimate scenarios, ultimately contributing to the optimization of cropmanagement practices.

Learning-based agricultural management in partially observable environments subject to climate variability