One of the primary factors in the hydrological cycle is reference evapotranspiration (ET₀). The prediction of ET₀ is crucial to manage irrigation water in agriculture under climate change; however, little research has been conducted on the trends of ET₀ changes in Shandong Province. In this study, to estimate ET₀ in the entire Shandong Province, 245 sites were chosen, and the monthly ET₀ values during 1901–2020 were computed using the Hargreaves–Samani formula. A deep learning model, termed SAO-CNN-BiGRU-Attention, was utilized to forecast the monthly ET₀ during 2021–2100, and the predictions were compared to two CMIP6 climate scenarios, SSP2-4.5 and SSP5-8.5. The hierarchical clustering results revealed that Shandong Province encompassed three homogeneous regions. The ET₀ values of Clusters H1 and H2, which were situated in inland regions and major agricultural areas, were the highest. The SAO-CNN-BiGRU-Attention and SSP5-8.5 forecasting results generally displayed a monotonically growing trend during the forecast period in the three regions; however, the SAO-CNN-BiGRU-Attention model displayed a declining tendency at a few points. According to the SAO-CNN-BiGRU-Attention and SSP5-8.5 results, during 2091–2100, H1, H2, and H3 will reach their peaks; the SSP2-4.5 results show that H1, H2, and H3 will peak in 2031–2040. At the end of the forecast period, for Clusters H1, H2, and H3, the prediction rate of SAO-CNN-BiGRU-Attention increased by 1.31, 1.56%, and 1.80%, respectively, whereas SSP2-4.5’s prediction rate increased by 0.31%, 0.95%, and 1.57%, respectively, and SSP5-8.5’s prediction rate increased by 10.88%, 10.76%, and 10.69%, respectively. The prediction results of SAO-CNN-BiGRU-Attention were similar to those of SSP2-4.5 (R² > 0.96). The SAO-CNN-BiGRU-Attention deep learning model can be used to forecast future ET₀.

To achieve regional sustainable development, the low-carbon transformation of agriculture is essential, as it serves both as a significant carbon source and as a potential carbon sink. This study calculated the agricultural carbon emissions in Liaocheng from 2010 to 2022 by analyzing processes including crop cultivation, animal husbandry, and agricultural input. Additionally, a simulation model of the water–energy–food–carbon nexus (WEFC-Nexus) for Liaocheng’s agricultural production process was developed. Using Vensim PLE 10.0.0 software, this study constructed a WEFC-Nexus model encompassing four major subsystems: economic development, agricultural production, agricultural inputs, and water use. The model explored four policy scenarios: business-as-usual scenario (S1), ideal agricultural development (S2), strengthening agricultural investment (S3), and reducing agricultural input costs (S4). It also forecast the trends in carbon emissions and primary sector GDP under these different scenarios from 2023 to 2030. The conclusions were as follows: (1) Total agricultural carbon emissions exhibited a three-phase trajectory, namely, “rapid growth (2010–2014)–sharp decline (2015–2020)–gradual rebound (2021–2022)”, with sectoral contributions ranked as livestock farming (50%) > agricultural inputs (27%) > crop cultivation (23%). (2) The carbon emissions per unit of primary sector GDP (CEAG) for S2, S3, and S4 decreased by 8.86%, 5.79%, and 7.72%, respectively, compared to S1. The relationship between the carbon emissions under the four scenarios is S3 > S1 > S2 > S4. The relationship between the four scenarios in the primary sector GDP is S3 > S2 > S4 > S1. S2 can both control carbon emissions and achieve growth in primary industry output. Policy recommendations emphasize reducing chemical fertilizer use, optimizing livestock management, enhancing agricultural technology efficiency, and adjusting agricultural structures to balance economic development with environmental sustainability.