Simulating the Marginal Green Contribution of AI Modules in a Smart-Agriculture Platform: Evidence from Two Monte Carlo Experiments

Zhaoyang Li; Ruijie Zhang; Zhaoji Sun; Lu Zhang

cs.AISep 6, 2026

Simulating the Marginal Green Contribution of AI Modules in a Smart-Agriculture Platform: Evidence from Two Monte Carlo Experiments

Authors: Zhaoyang Li, Ruijie Zhang, Zhaoji Sun, Lu Zhang

Organizations: Sanya University, Sanya, Hainan 572022, China · Handan Weizhi Jingjie AI Basic Software Co., Ltd.

Abstract

Smart agriculture platforms usually bundle AI diagnosis, IoT sensing and decision push into a single package, so the green benefit attributable to each component remains unclear and resource-allocation decisions lack quantitative evidence. Building on a previous platform-level Monte Carlo assessment, this paper makes the components explicit and runs two controlled simulation experiments. Experiment 1 follows the chain from AI capability to farmer behavior to agrochemical input reduction, modeling pesticide/fertilizer reduction as avoidable blind-application share times prescription effectiveness times decision-touch coverage times adoption rate, and compares an experienced-extension mode with the AI mode: the probability of reaching 20% pesticide reduction is essentially zero in the extension mode but 20.7% at baseline, up to 49% with diagnosis accuracy 0.95 and adoption 0.85 under AI; the probability of 15% fertilizer reduction rises from near zero to 52.0%. Experiment 2 compares current practice (P0), IoT engineering retrofit (P1), and P1 plus AI irrigation scheduling (P2): median aggregate water saving rises from 7.8% (P0) to 11.0% (P1) and 16.0% (P2), with AI adding 5.0 percentage points beyond engineering; paddy CH4 reduction reaches 30.5% under AI scheduling versus 19.8% under manual operation, and the rice irrigation-methane subsystem carbon intensity declines 27.9%. Sensitivity analyses of both experiments consistently indicate that the primary bottleneck for meeting green targets is farmer adoption rather than algorithm accuracy, and that AI data fusion is robust to soil-moisture sensing errors. This work provides a reproducible simulation framework for component-level green-value evaluation and promotion-strategy optimization of smart agriculture platforms.

Figures & tables

Parameter	Meaning	lo	mode	hi	Grade
$\varphi_{avoid}$	avoidable blind sprays share	0.15	0.30	0.50	C
$\eta_{exp}$	extension prescription effectiveness	0.55	0.70	0.85	C
$\gamma_{exp}$	extension coverage	0.30	0.40	0.55	C
$\gamma_{AI}$	AI coverage	0.85	0.92	0.97	B/C
$acc$	AI diagnostic accuracy	0.78	0.88	0.95	B
$\alpha$	AI suggestion adoption rate	0.35	0.60	0.85	C

Table 1: Experiment 1 parameters (triangular lo/mode/hi)

Parameter	Meaning	lo	mode	hi	Grade
$C_{m}/C_{v}/C_{r}$	tech ceiling mango/veg/rice	0.27/0.22/0.13	0.40/0.35/0.23	0.55/0.50/0.35	A/B
$q$ (P0/P1/P2)	scheduling quality	0.30/0.50/0.80	0.42/0.62/0.88	0.55/0.75/0.95	C
$\alpha$	technology adoption rate	0.30	0.55	0.80	C
$\sigma_{IoT}$	soil-moisture observation error	0.02	0.04	0.07	B
$\kappa$ (P1/P2)	error sensitivity	1.0	—	0.4	C
$\psi_{CH4}$	AWD potential	0.20	0.35	0.55	B

Table 2: Experiment 2 parameters (lo/mode/hi, three stages)

Variable	Mean	Median	P5	P95
Pesticide reduction (extension)	0.093	0.090	0.055	0.138
Pesticide reduction (AI)	0.166	0.164	0.104	0.237
Fertilizer reduction (extension)	0.066	0.065	0.040	0.095
Fertilizer reduction (AI)	0.154	0.152	0.097	0.216
AI pesticide increment	0.074	0.071	0.041	0.115
AI fertilizer increment	0.088	0.085	0.051	0.133

Table 3: Experiment 1 Monte Carlo results (N=10 4 , seed 20260907)

Figure 1: Distribution comparison of extension vs. AI modes (left: pesticide; right: fertilizer)

$acc$ $\backslash$ $\alpha$	0.35	0.60	0.85
0.70	13.1% / 1%	15.9% / 15%	18.6% / 37%
0.85	13.5% / 2%	16.5% / 20%	19.4% / 43%
0.95	13.7% / 3%	16.9% / 23%	20.1% / 49%

Table 4: Experiment 1 scenario matrix: AI pesticide reduction mean / P(pesticide

\geq

20%)

Figure 2: Experiment 1 OAT sensitivity: effects on AI-mode pesticide reduction

Indicator (median)	P0 current	P1 IoT engineering	P2 +AI decision
Mango water saving	0.092	0.131	0.190
Vegetable water saving	0.081	0.114	0.166
Rice water saving	0.054	0.076	0.110
Aggregate water saving	0.078	0.110	0.160
Paddy CH 4 reduction	0.000	0.198	0.305
Rice subsystem carbon reduction	0.007	0.182	0.279

Table 5: Experiment 2 three-stage results (medians)

Figure 3: Boxplots of three-stage aggregate water saving and paddy CH 4 reduction

Figure 4: Carbon-reduction pathway decomposition in the rice scenario: irrigation electricity and paddy CH 4 (means, kg CO 2 e/mu-season)

Figure 5: Effect of soil-moisture observation error on aggregate water saving: AI decision is more robust

Precision Agriculture

Precision agriculture uses spatial and temporal data, sensors, AI, and robotics to tailor crop monitoring and farm inputs to local conditions.

See all 63 papers

Monte Carlo-Based Ex-Ante Assessment of the Green Benefits of an AI-Driven Smart Agriculture Platform in Hainan
Sep 6, 2026Zhaoyang Li, Ruijie Zhang, Zhaoji Sun +1Precision Agriculture
Sanya University, Sanya, Hainan 572022, China · Handan Weizhi Jingjie AI Basic Software Co., Ltd.
Zhinong AI: A Design-Science Study of an AI-Enabled Agricultural Decision-Support Platform for Smallholder Production
May 19, 2026Zhaoyang Li, Jiaqi Liu, Ruijie ZhangAI-Assisted Decision Making Human-Centered AI
University of Sanya · Hebei International Studies University
Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations
Aug 31, 2026Ao Qu, Panagiotis Michelakis, Linyuan Han +8Software Engineering Multi-Agent Orchestration
Faculty of Computing Harbin Institute of Technology State Key Laboratory of Smart Farm Technologies and Systems Harbin, China · School of Electrical and Computer Engineering National Technical University of Athens Athens, Greece

Sep 6, 2026J/K move · Enter open · S save

Monte Carlo-Based Ex-Ante Assessment of the Green Benefits of an AI-Driven Smart Agriculture Platform in Hainan

Zhaoyang Li, Ruijie Zhang, Zhaoji Sun, Lu Zhang

Sanya University, Sanya, Hainan 572022, China · Handan Weizhi Jingjie AI Basic Software Co., Ltd.

Precision Agriculture

Open paper AskPDF arXiv

Smart agriculture platforms are widely regarded as key carriers for implementing China's pesticide and fertilizer reduction, water-saving and carbon-reduction agendas, yet a unified quantitative framework for assessing their green value is still lacking. Taking an AI-driven decision platform for tropical agriculture as the object (integrating large-language-model question answering, multimodal pest diagnosis, IoT sensing, satellite remote sensing, and a closed-loop field record system), this study builds a cradle-to-farm-gate agricultural carbon accounting model covering pesticide and fertilizer production, field N2O, irrigation electricity and paddy CH4, translates platform interventions into quantifiable transmission parameters, and propagates parameter uncertainty by Monte Carlo simulation over three Hainan scenarios (mango, winter vegetable, rice/nanfan, area-weighted 40%:30%:30%). Under full adoption, median reductions are 23.5% (90% interval 15.0%-33.2%) for pesticide use, 21.0% (13.8%-28.9%) for fertilizer, 16.5% (10.9%-23.5%) for irrigation water, and 21.5% (16.1%-27.2%) for carbon intensity. Attainment probabilities are high for fertilizer reduction >=15% (90.6%) and clear carbon decline (98.1%), but only about 20% for aggregate water saving >=20%, favoring scenario-specific statements. Sobol first-order indices show soil-test recommendation and organic substitution jointly explain about 83% of the variance of aggregate carbon-intensity reduction. Convergence tests show 10,000 iterations stabilize all statistics; conservative/baseline/optimistic scenario bounds are reported. The framework offers a reproducible, calibration-ready methodology for ex-ante green-value assessment and pilot observation design.

Abstract

Precision Agriculture

Explore similar work

Monte Carlo-Based Ex-Ante Assessment of the Green Benefits of an AI-Driven Smart Agriculture Platform in Hainan

Zhinong AI: A Design-Science Study of an AI-Enabled Agricultural Decision-Support Platform for Smallholder Production

Deploying and Evaluating a Smart-Agriculture Agentic Engine for Full-Season Soybean Farm Operations