基于多模态时空对齐与因果利润建模的农业投入优化(MAION)

1. Introduction

With the continuous advancement of smart agriculture, agricultural production is shifting from experience-dependent judgment toward integrated management supported by data, models, and intelligent decision-making [1]. Internet of Things sensors, unmanned aerial vehicle remote sensing, field image acquisition devices, meteorological monitoring systems, and agricultural management platforms have been increasingly deployed in farmland and orchard production scenarios, enabling continuous recording of soil moisture, temperature and humidity, light intensity, rainfall, crop growth status, pest and disease conditions, irrigation and fertilization records, and pesticide application information [2]. These data provide a fine-grained perception basis for precision agriculture and allow crop growth processes and farmland environmental changes to be understood more comprehensively [3]. However, data availability does not necessarily mean that collected data can be directly transformed into effective decisions [4]. In practical production, managers are usually concerned not only with the accurate prediction of a single indicator, but also with how fertilization, irrigation, and pesticide application should be arranged under current crop status, meteorological conditions, and soil background so that input costs can be controlled while yield and quality are maintained [5]. With increasing production costs, tightening resource constraints, and intensifying climate variability, simply pursuing yield maximization is no longer sufficient for modern agricultural management. A more reasonable balance among yield, cost, resource utilization, and net profit has therefore become an important issue in smart agricultural decision-making research [6].

Traditional agricultural management usually relies on farmer experience, expert rules, and statistical analysis models [7]. Experience-driven methods are widely used because of their direct operation and low implementation cost, but their effectiveness depends heavily on personal experience and shows limited adaptability to climate variation, plot heterogeneity, and crop growth-stage changes [8]. Expert systems can provide recommendations for irrigation, fertilization, and pest or disease control according to predefined rules; however, their rule structures are usually fixed and may lack flexibility when complex coupling relationships exist among environmental variables, crop states, and input behaviors. Statistical models and production function models can analyze relationships between agricultural inputs and outputs, but they often rely on linear or static assumptions and are insufficient for describing nonlinear responses, time-lag effects, and stage-dependent differences in agricultural systems [9]. Moreover, many traditional methods still focus on a single production indicator, such as yield, disease incidence, or soil moisture, while the joint relationships among crop status, environmental conditions, input behavior, and economic return are rarely considered. Therefore, traditional methods remain inadequate for multi-source data fusion, dynamic input optimization, and profit-oriented intelligent decision-making [10].

Deep learning has provided a new technical pathway for smart agriculture and has been widely applied to crop recognition, pest and disease detection, yield prediction, quality assessment, and environmental monitoring [11]. Convolutional neural networks can extract crop growth, canopy structure, and disease features from field images and unmanned aerial vehicle remote sensing images, while recurrent neural networks, long short-term memory networks, and Transformer models can process meteorological, soil, and crop growth time-series data. Multimodal learning methods have further attempted to integrate images, sensor data, and management records to improve agricultural state perception and yield prediction [12]. These studies have promoted the transition from manual observation to automated analysis, but limitations remain in input optimization. Several recent studies have explored causal modeling, reinforcement learning, and multimodal learning for agricultural or related complex decision-making tasks. Zhang et al. [13] proposed the CMRL causal meta-reinforcement learning framework, integrating reinforcement learning feedback, causal intervention, and meta-learning optimization for multimodal remote sensing classification, with overall accuracies of

$86.27 %$
,

$95.51 %$
, and

$99.41 %$
on the MUUFL, Houston, and Trento datasets, respectively. Liu et al. [14] proposed the ASGO-PAPIS framework, which combined deep learning and causal inference for multidimensional dairy production cost analysis and improved Precision, NDCG, and MAP by up to approximately 5 percentage points. Zhang et al. [15] developed a cross-modal attention and PPO reinforcement learning framework for pesticide application optimization by fusing unmanned aerial vehicle hyperspectral data, soil meteorological data, and pest monitoring data, achieving an RMSE of

$0.162$
, a spraying accuracy of

$88.3 %$
, an

$18.3 %$
reduction in pesticide usage, and a pest suppression effect of

$77.9 %$
.

Although multimodal learning, causal inference, and reinforcement learning have each demonstrated considerable potential for intelligent agricultural management, they address different stages of the decision-making process and therefore exhibit complementary strengths as well as inherent limitations. Multimodal fusion effectively integrates heterogeneous information from crop images, environmental observations, soil conditions, and management records, enabling comprehensive agricultural state perception [16]. However, it primarily models statistical correlations and cannot reliably determine how changes in irrigation, fertilization, or pesticide application causally affect agricultural productivity and economic returns. Causal inference alleviates confounding effects caused by weather variability, soil heterogeneity, and management differences, providing more reliable estimates of intervention effects. Nevertheless, existing causal approaches mainly focus on effect estimation rather than generating optimal sequential management strategies throughout an entire growing season [17]. Reinforcement learning is naturally suitable for optimizing long-term agricultural decisions, yet its performance strongly depends on accurate state representations and reliable reward signals. Inaccurate perception or biased intervention estimation may consequently result in unstable or economically suboptimal policies. Therefore, these three paradigms should be regarded as complementary rather than competing approaches. A unified framework integrating multimodal perception, causal reasoning, and reinforcement learning can simultaneously achieve comprehensive agricultural state representation, reliable intervention effect estimation, and long-term profit-oriented decision optimization.

Accordingly, a multimodal causal reinforcement learning framework for agricultural input–profit optimization, namely the Multimodal Agricultural Input–Output Optimization Network, abbreviated as MAION, is proposed in this study. Visual data, environmental data, soil data, and agricultural management records are used as inputs, while yield, cost, net profit, and optimal input strategies are taken as outputs. An end-to-end modeling method from multi-source agricultural perception to economically optimal decision-making is thereby constructed. Unlike models that focus only on yield prediction or state recognition, MAION incorporates agricultural input behavior, production cost, and economic return into a unified learning objective. Through cross-modal spatiotemporal alignment, causal input–profit modeling, and profit-driven reinforcement learning decision-making, agricultural intelligent perception is connected with practical production decisions, thereby providing an executable modeling strategy for precision input, cost control, and net profit improvement. The main contributions of this study are summarized as follows:

• To address the lack of unified agricultural state representation caused by heterogeneous data sources with inconsistent temporal and semantic characteristics, a unified multimodal agricultural input–output modeling framework is developed to support profit-oriented decision making.

• To address the spatiotemporal inconsistency among crop images, environmental observations, soil measurements, and management records, a cross-modal spatiotemporal alignment strategy is introduced to establish consistent multimodal agricultural representations.

• To address the inability of existing predictive models to distinguish causal intervention effects from statistical correlations, a causal-aware input–profit modeling mechanism is developed to provide more reliable estimation of the economic effects of agricultural management actions.

• To address the limitation of conventional optimization methods in achieving long-term economic management, a profit-driven reinforcement learning strategy is designed to optimize sequential agricultural input decisions under long-term profit objectives.

• To address the challenge of robust deployment in practical agricultural environments, comprehensive cross-plot, cross-year, and missing-modality experiments are conducted to validate the generalization capability and practical effectiveness of the proposed framework.

2. Related Work

2.1. Multimodal Perception Methods in Smart Agriculture

Multimodal perception in smart agriculture refers to the continuous observation and integrated representation of agricultural production systems using heterogeneous data sources, including images, sensors, remote sensing, and management records [18]. Although these data differ in acquisition frequency, spatial coverage, and semantic level, they jointly provide important information for agricultural state perception [19]. Therefore, multimodal perception is valuable not only because more data types are introduced, but also because complementary information from different sources can be used to identify crop growth status, environmental changes, and production risks more reliably [20]. Image-based agricultural perception methods have been widely studied [21]. Convolutional neural networks can automatically extract texture, color, edge, and morphological features from crop images, and have been applied to disease recognition, fruit detection, weed identification, and quality grading [22]. Vision Transformers further improve the representation of long-range regional dependencies and complex background information, thereby enhancing adaptability under occlusion, illumination variation, and scale differences in field environments [23]. Sensor-based time-series data are also important for greenhouse control, soil moisture monitoring, and crop growth trend analysis, where continuous environmental variables need to be modeled dynamically [24]. Long short term memory (LSTM), gated recurrent unit (GRU), and Transformer models have been adopted to capture long-term dependencies among meteorological variables, soil variables, and growth indicators [25]. Remote sensing methods are more commonly used for regional growth estimation, drought monitoring, and yield assessment through spectral features, vegetation indices, and spatial textures [26]. Despite these advances, most existing studies remain centered on a single modality or a single task [27]. Image models usually focus on disease categories, fruit numbers, or phenotypic traits; sensor models are mainly used for environmental trend prediction or soil state estimation; and remote sensing models emphasize regional crop growth variation [28]. Such fragmented strategies are effective for specific tasks, but they are insufficient for describing the coupled relationships among crops, environments, soils, and management behaviors [29]. For agricultural input–profit optimization, crop growth status or environmental risk alone is not enough; it is also necessary to understand how these states influence fertilization, irrigation, and pesticide application, and how such behaviors are ultimately reflected in yield, cost, and net profit [30]. Accordingly, limitations remain in cross-modal spatiotemporal alignment, unified state representation, and feature fusion oriented toward economic decision-making [31,32].

2.2. Agricultural Yield Prediction and Input Modeling Methods

Agricultural yield prediction and input modeling aim to estimate crop production by modeling the relationships among environmental conditions, soil properties, management practices, and historical crop growth states [33]. Early studies mainly relied on statistical regression, crop growth models, and production function models to quantify the effects of climate, soil, irrigation, and fertilization on yield [34,35]. Although these methods are interpretable, they have limited ability to capture the nonlinear and dynamic interactions among meteorological conditions, soil characteristics, crop varieties, pests, and management practices that jointly determine agricultural production [36]. Recent studies have introduced machine learning and deep learning methods to improve yield modeling [37]. Tree-based models such as Random Forest and XGBoost, together with support vector machines, have demonstrated robust performance on structured agricultural data [38], while sequential models including LSTM, GRU, and Transformer further improve the modeling of temporal dependencies and long-term environmental effects from multi-source observations [39,40]. These advances have substantially improved prediction accuracy for agricultural production. However, existing studies remain primarily prediction-oriented. Most methods optimize yield without explicitly considering production costs or economic returns, despite the fact that maximizing yield does not necessarily maximize profit [41,42]. In addition, current models generally learn statistical correlations between agricultural inputs and outputs rather than identifying the underlying causal relationships, making them vulnerable to confounding factors such as weather, soil conditions, and management differences [43]. Consequently, they provide limited support for reliable input optimization [44]. To address these limitations, the proposed causal-aware input–profit modeling module treats fertilization, irrigation, and pesticide application as intervenable variables, jointly estimating their effects on yield, cost, and profit from multimodal agricultural state representations, thereby extending agricultural modeling from prediction toward interpretable decision-oriented optimization [45].

2.3. Agricultural Economic Optimization and Intelligent Decision-Making Methods

Agricultural economic optimization aims to allocate land, water, fertilizer, pesticides, labor, and other production resources to balance yield, quality, cost, and profit under resource constraints [46]. Traditional approaches mainly rely on production functions, cost–benefit analysis, and input–output efficiency evaluation to quantify the economic effects of agricultural inputs and support production planning [47,48]. Although these methods provide clear economic interpretations, they generally assume relatively stable environmental conditions and fixed input–output relationships, making them difficult to apply to real agricultural systems where weather, market conditions, and crop responses vary continuously across growth stages [49]. Consequently, agricultural input optimization is increasingly regarded as a dynamic sequential decision-making problem rather than a static optimization task [50]. Reinforcement learning (RL) provides an effective framework for learning long-term agricultural management strategies by optimizing cumulative rewards through continuous interactions with the environment [51,52]. Existing studies formulate crop status, soil conditions, meteorological observations, and historical management records as states [53], while irrigation, fertilization, and pesticide application are treated as actions, enabling optimization of long-term objectives such as yield, quality, resource consumption, and economic return [54]. Compared with prediction-based approaches, RL is better suited to sta