RESUMEN
The fraction of absorbed photosynthetically active radiation (FAPAR) and the photosynthesis rate (Pn) of maize canopies were identified as essential photosynthetic parameters for accurately estimating vegetation growth and productivity using multispectral vegetation indices (VIs). Despite their importance, few studies have compared the effectiveness of multispectral imagery and various machine learning techniques in estimating these photosynthetic traits under high vegetation coverage. In this study, seventeen multispectral VIs and four machine learning (ML) algorithms were utilized to determine the most suitable model for estimating maize FAPAR and Pn during the kharif and rabi seasons at Tamil Nadu Agricultural University, Coimbatore, India. Results demonstrate that indices such as OSAVI, SAVI, EVI-2, and MSAVI-2 during the kharif and MNDVIRE and MSRRE during the rabi season outperformed others in estimating FAPAR and Pn values. Among the four ML methods of random forest (RF), extreme gradient boosting (XGBoost), support vector regression (SVR), and multiple linear regression (MLR) considered, RF consistently showed the most effective fitting effect and XGBoost demonstrated the least fitting accuracy for FAPAR and Pn estimation. However, SVR with R2 = 0.873 and RMSE = 0.045 during the kharif and MLR with R2 = 0.838 and RMSE = 0.053 during the rabi season demonstrated higher fitting accuracy, particularly notable for FAPAR prediction. Similarly, in the prediction of Pn, MLR showed higher fitting accuracy with R2 = 0.741 and RMSE = 2.531 during the kharif and R2 = 0.955 and RMSE = 1.070 during the rabi season. This study demonstrated the potential of combining UAV-derived VIs with ML to develop accurate FAPAR and Pn prediction models, overcoming VI saturation in dense vegetation. It underscores the importance of optimizing these models to improve the accuracy of maize vegetation assessments during various growing seasons.
RESUMEN
Regenerative agricultural practices, i.e. organic and natural farming, are rooted in India since ancient times. However, the high cost of production, lack of organic pest control measures and premium price of organic produces in chemical agriculture encourage natural farming. In the present study, the quality improvement of calcareous soils under organic (OGF) and natural (NTF) management was compared with integrated conventional (ICF) and non-invasive (NIF) farming practices with cotton-sorghum crops over three consecutive years. A total of 23 soil attributes were analyzed at the end of the third cropping cycle and subjected to principal component analysis (PCA) to select a minimum data set (MDS) and obtain a soil quality index (SQI). The attributes soil organic carbon (SOC), available Fe, pH, bulk density (BD) and alkaline phosphatase (APA) were selected as indicators based on correlations and expert opinions on the lime content of the experimental soil. The SQI was improved in the order of OGF (0.89) > NTF(0.69) > ICF(0.48) > NIF(0.05). The contribution of the indicators to SQI was in the order of available Fe (17-44%) > SOC (21-28%), APA (11-36%) > pH (0-22%), and BD (0-20%) regardless of the farming practices. These indicators contribute equally to soil quality under natural (17-22%) and organic (18-22%) farming. The benefit:cost ratio was calculated to show the advantage of natural farming and was in the order of NTF(1.95-2.29), ICF (1.34-1.47), OGF (1.13-1.20) and NIF (0.84-1.47). In overall, the natural farming significantly sustained the soil quality and cost benefit compared to integrated conventional farming practices.